Refine critique and audit skills based on review feedback

- Collapse inline cognitive load section into reference pointer
- Differentiate audit (technical, code-level) from critique (UX, holistic)
- Add MANDATORY PREPARATION block to audit for context gathering
- Rename Riley persona to "Deliberate Stress Tester", remove pricing focus
- Restore stripped checklist items, persona examples, and emotional journey detail
- Restore "Don't soften criticism" and IMPORTANT/NEVER lines in audit
- Restore constraints question in Phase 3
- Fix em dash formatting (use proper — not --)
- Shorten descriptions while preserving key trigger terms

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.agents/skills/audit/SKILL.md

@@ -1,17 +1,23 @@
 ---
 name: audit
-description: Perform a comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates a scored report with severity ratings and actionable plan. Use when the user wants a design review, accessibility check, quality audit, or a full list of UI issues to fix.
+description: Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
 user-invocable: true
 argument-hint: "[area (feature, page, component...)]"
 ---
 
-Run systematic quality checks and generate a comprehensive audit report with quantitative scoring, prioritized issues, and an actionable plan. Don't fix issues — document them for other commands to address.
+## MANDATORY PREPARATION
 
-**First**: Invoke /frontend-design for design principles and anti-patterns.
+Invoke /frontend-design — it contains design principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no design context exists yet, you MUST run /teach-impeccable first.
+
+---
+
+Run systematic **technical** quality checks and generate a comprehensive report. Don't fix issues — document them for other commands to address.
+
+This is a code-level audit, not a design critique. Check what's measurable and verifiable in the implementation.
 
 ## Diagnostic Scan
 
-Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using the criteria below.
+Run comprehensive checks across 5 dimensions. Score each dimension 0-4 using the criteria below.
 
 ### 1. Accessibility (A11y)
 
@@ -23,7 +29,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Alt text**: Missing or poor image descriptions
 - **Form issues**: Inputs without labels, poor error messaging, missing required indicators
 
-**Score 0–4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
+**Score 0-4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
 
 ### 2. Performance
 
@@ -34,7 +40,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Bundle size**: Unnecessary imports, unused dependencies
 - **Render performance**: Unnecessary re-renders, missing memoization
 
-**Score 0–4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
+**Score 0-4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
 
 ### 3. Theming
 
@@ -44,7 +50,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Inconsistent tokens**: Using wrong tokens, mixing token types
 - **Theme switching issues**: Values that don't update on theme change
 
-**Score 0–4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
+**Score 0-4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
 
 ### 4. Responsive Design
 
@@ -55,113 +61,73 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Text scaling**: Layouts that break when text size increases
 - **Missing breakpoints**: No mobile/tablet variants
 
-**Score 0–4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
+**Score 0-4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
 
 ### 5. Anti-Patterns (CRITICAL)
 
 Check against ALL the **DON'T** guidelines in the frontend-design skill. Look for AI slop tells (AI color palette, gradient text, glassmorphism, hero metrics, card grids, generic fonts) and general design anti-patterns (gray on color, nested cards, bounce easing, redundant copy).
 
-**Score 0–4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
+**Score 0-4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
 
-**CRITICAL**: This is an audit, not a fix. Document issues thoroughly with clear explanations of impact. Use other commands to fix issues after audit.
-
-## Generate Comprehensive Report
+## Generate Report
 
 ### Audit Health Score
 
-Present the dimension scores as a table:
-
 | # | Dimension | Score | Key Finding |
 |---|-----------|-------|-------------|
-| 1 | Accessibility | ? | [most critical a11y issue or "—"] |
+| 1 | Accessibility | ? | [most critical a11y issue or "--"] |
 | 2 | Performance | ? | |
 | 3 | Responsive Design | ? | |
 | 4 | Theming | ? | |
 | 5 | Anti-Patterns | ? | |
 | **Total** | | **??/20** | **[Rating band]** |
 
-**Rating bands**:
-| Score | Rating | Action |
-|-------|--------|--------|
-| 18–20 | Excellent | Minor polish only |
-| 14–17 | Good | Address weak dimensions |
-| 10–13 | Acceptable | Significant work needed |
-| 6–9 | Poor | Major quality overhaul |
-| 0–5 | Critical | Fundamental issues across the board |
+**Rating bands**: 18-20 Excellent (minor polish), 14-17 Good (address weak dimensions), 10-13 Acceptable (significant work needed), 6-9 Poor (major overhaul), 0-5 Critical (fundamental issues)
 
 ### Anti-Patterns Verdict
-**Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
+**Start here.** Pass/fail: Does this look AI-generated? List specific tells. Be brutally honest.
 
 ### Executive Summary
 - Audit Health Score: **??/20** ([rating band])
 - Total issues found (count by severity: P0/P1/P2/P3)
-- Most critical issues (top 3-5)
+- Top 3-5 critical issues
 - Recommended next steps
 
 ### Detailed Findings by Severity
 
-Tag every issue with **P0–P3 severity**:
-| Priority | Name | Description |
-|----------|------|-------------|
-| **P0** | Blocking | Prevents task completion — fix immediately |
-| **P1** | Major | Significant difficulty or WCAG AA violation — fix before release |
-| **P2** | Minor | Annoyance, workaround exists — fix in next pass |
-| **P3** | Polish | Nice-to-fix, no real user impact — fix if time permits |
+Tag every issue with **P0-P3 severity**:
+- **P0 Blocking**: Prevents task completion — fix immediately
+- **P1 Major**: Significant difficulty or WCAG AA violation — fix before release
+- **P2 Minor**: Annoyance, workaround exists — fix in next pass
+- **P3 Polish**: Nice-to-fix, no real user impact — fix if time permits
 
 For each issue, document:
 - **[P?] Issue name**
-- **Location**: Where it occurs (component, file, line)
+- **Location**: Component, file, line
 - **Category**: Accessibility / Performance / Theming / Responsive / Anti-Pattern
-- **Description**: What the issue is
 - **Impact**: How it affects users
 - **WCAG/Standard**: Which standard it violates (if applicable)
 - **Recommendation**: How to fix it
-- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive — or other installed skills you're sure exist)
-
-#### P0 — Blocking Issues
-[Issues that prevent task completion or violate WCAG A]
-
-#### P1 — Major Issues
-[Significant usability/accessibility impact, WCAG AA violations]
-
-#### P2 — Minor Issues
-[Quality issues, WCAG AAA violations, performance concerns]
-
-#### P3 — Polish Issues
-[Minor inconsistencies, optimization opportunities]
+- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Patterns & Systemic Issues
 
-Identify recurring problems:
+Identify recurring problems that indicate systemic gaps rather than one-off mistakes:
 - "Hard-coded colors appear in 15+ components, should use design tokens"
 - "Touch targets consistently too small (<44px) throughout mobile experience"
-- "Missing focus indicators on all custom interactive components"
 
 ### Positive Findings
 
-Note what's working well:
-- Good practices to maintain
-- Exemplary implementations to replicate elsewhere
+Note what's working well — good practices to maintain and replicate.
 
 ## Recommended Actions
 
-Present a prioritized action summary. Order is determined by severity automatically (P0 first, then P1, then P2).
-
-### Action Summary
-
-List recommended commands in priority order:
+List recommended commands in priority order (P0 first, then P1, then P2):
 
 1. **[P?] `/command-name`** — Brief description (specific context from audit findings)
 2. **[P?] `/command-name`** — Brief description (specific context)
-...
 
-**Rules for recommendations**:
-- Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive
-- Order by severity: P0 issues first, then P1, then P2 (skip P3 unless user has few issues)
-- Each item's description should carry enough context that the command knows what to focus on
-- Map findings to the most appropriate command
-- Skip commands that would address zero issues
-- End with `/polish` as the final step if any fixes were recommended
+**Rules**: Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive. Map findings to the most appropriate command. End with `/polish` as the final step if any fixes were recommended.
 
 After presenting the summary, tell the user:
 
@@ -173,10 +139,9 @@ After presenting the summary, tell the user:
 
 **NEVER**:
 - Report issues without explaining impact (why does this matter?)
-- Mix severity levels inconsistently
-- Skip positive findings (celebrate what works)
 - Provide generic recommendations (be specific and actionable)
+- Skip positive findings (celebrate what works)
 - Forget to prioritize (everything can't be P0)
 - Report false positives without verification
 
-Remember: You're a quality auditor with exceptional attention to detail. Document systematically, prioritize ruthlessly, and provide clear paths to improvement. A good audit makes fixing easy.
+Remember: You're a technical quality auditor. Document systematically, prioritize ruthlessly, cite specific code locations, and provide clear paths to improvement.

.agents/skills/critique/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: critique
-description: Evaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, cognitive load, and overall design quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design, UI, or component.
+description: Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
 user-invocable: true
 argument-hint: "[area (feature, page, component...)]"
 ---
@@ -11,7 +11,7 @@ Invoke /frontend-design — it contains design principles, anti-patterns, and th
 
 ---
 
-Conduct a holistic design critique, evaluating whether the interface actually works—not just technically, but as a designed experience. Think like a design director giving feedback.
+Conduct a holistic design critique, evaluating whether the interface actually works — not just technically, but as a designed experience. Think like a design director giving feedback.
 
 ## Phase 1: Design Critique
 
@@ -21,7 +21,7 @@ Evaluate the interface across these dimensions:
 
 **This is the most important check.** Does this look like every other AI-generated interface from 2024-2025?
 
-Review the design against ALL the **DON'T** guidelines in the frontend-design skill—they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
+Review the design against ALL the **DON'T** guidelines in the frontend-design skill — they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
 
 **The test**: If you showed this to someone and said "AI made this," would they believe you immediately? If yes, that's the problem.
 
@@ -31,20 +31,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Do size, color, and position communicate importance correctly?
 - Is there visual competition between elements that should have different weights?
 
-### 3. Information Architecture
-→ *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and checklist*
+### 3. Information Architecture & Cognitive Load
+> *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and 8-item checklist*
 - Is the structure intuitive? Would a new user understand the organization?
 - Is related content grouped logically?
 - Are there too many choices at once? Count visible options at each decision point — if >4, flag it
 - Is the navigation clear and predictable?
 - **Progressive disclosure**: Is complexity revealed only when needed, or dumped on the user upfront?
-- **Cognitive load sub-check**: Run the 8-item cognitive load checklist from the reference. Report the number of failures.
+- **Run the 8-item cognitive load checklist** from the reference. Report failure count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
 
 ### 4. Emotional Journey
-→ *Consult [cognitive-load](reference/cognitive-load.md) for emotional intervention patterns*
 - What emotion does this interface evoke? Is that intentional?
 - Does it match the brand personality?
-- Does it feel trustworthy, approachable, premium, playful—whatever it should feel?
+- Does it feel trustworthy, approachable, premium, playful — whatever it should feel?
 - Would the target user feel "this is for me"?
 - **Peak-end rule**: Is the most intense moment positive? Does the experience end well (confirmation, celebration, clear next step)?
 - **Emotional valleys**: Check for onboarding frustration, error cliffs, feature discovery gaps, or anxiety spikes at high-stakes moments (payment, delete, commit)
@@ -72,7 +71,7 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Is color used to communicate, not just decorate?
 - Does the palette feel cohesive?
 - Are accent colors drawing attention to the right things?
-- Does it work for colorblind users? (not just technically—does meaning still come through?)
+- Does it work for colorblind users? (not just technically — does meaning still come through?)
 
 ### 9. States & Edge Cases
 - Empty states: Do they guide users toward action, or just say "nothing here"?
@@ -86,27 +85,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Are labels and buttons unambiguous?
 - Does error copy help users fix the problem?
 
-### 11. Cognitive Load
-→ *Consult [cognitive-load](reference/cognitive-load.md)*
-- **Intrinsic vs. extraneous**: Is the mental effort coming from the task itself (acceptable) or from poor design choices (eliminate)?
-- **Decision points**: Count visible choices at key moments. More than 4 simultaneous options = overload.
-- **Working memory burden**: Does the user need to remember information from a previous screen to act on the current one?
-- **Information chunking**: Is content broken into digestible groups, or presented as undifferentiated walls?
-- Run the 8-item cognitive load checklist. Report failures count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
-
 ## Phase 2: Present Findings
 
 Structure your feedback as a design director would:
 
 ### Design Health Score
-→ *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
+> *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
 
 Score each of Nielsen's 10 heuristics 0–4. Present as a table:
 
 | # | Heuristic | Score | Key Issue |
 |---|-----------|-------|-----------|
 | 1 | Visibility of System Status | ? | [specific finding or "—" if solid] |
-| 2 | Match System ↔ Real World | ? | |
+| 2 | Match System / Real World | ? | |
 | 3 | User Control and Freedom | ? | |
 | 4 | Consistency and Standards | ? | |
 | 5 | Error Prevention | ? | |
@@ -123,13 +114,13 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score
 **Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
 
 ### Overall Impression
-A brief gut reaction—what works, what doesn't, and the single biggest opportunity.
+A brief gut reaction — what works, what doesn't, and the single biggest opportunity.
 
 ### What's Working
-Highlight 2-3 things done well. Be specific about why they work.
+Highlight 2–3 things done well. Be specific about why they work.
 
 ### Priority Issues
-The 3-5 most impactful design problems, ordered by importance.
+The 3–5 most impactful design problems, ordered by importance.
 
 For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](reference/heuristics-scoring.md) for severity definitions):
 - **[P?] What**: Name the problem clearly
@@ -138,7 +129,7 @@ For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](refe
 - **Suggested command**: Which command could address this (from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Persona Red Flags
-→ *Consult [personas](reference/personas.md)*
+> *Consult [personas](reference/personas.md)*
 
 Auto-select 2–3 personas most relevant to this interface type (use the selection table in the reference). If `.github/copilot-instructions.md` contains a `## Design Context` section from `teach-impeccable`, also generate 1–2 project-specific personas from the audience/brand info.
 
@@ -154,12 +145,12 @@ Be specific — name the exact elements and interactions that fail each persona.
 Quick notes on smaller issues worth addressing.
 
 **Remember**:
-- Be direct—vague feedback wastes everyone's time
-- Be specific—"the submit button" not "some elements"
+- Be direct — vague feedback wastes everyone's time
+- Be specific — "the submit button" not "some elements"
 - Say what's wrong AND why it matters to users
 - Give concrete suggestions, not just "consider exploring..."
-- Prioritize ruthlessly—if everything is important, nothing is
-- Don't soften criticism—developers need honest feedback to ship great design
+- Prioritize ruthlessly — if everything is important, nothing is
+- Don't soften criticism — developers need honest feedback to ship great design
 
 ## Phase 3: Ask the User
 
@@ -167,9 +158,9 @@ Quick notes on smaller issues worth addressing.
 
 Ask questions along these lines (adapt to the specific findings — do NOT ask generic questions):
 
-1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2-3 issue categories as options.
+1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2–3 issue categories as options.
 
-2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2-3 tonal directions as options based on what would fix the issues found.
+2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2–3 tonal directions as options based on what would fix the issues found.
 
 3. **Scope**: Ask how much the user wants to take on. For example: "I found N issues. Want to address everything, or focus on the top 3?" Offer scope options like "Top 3 only", "All issues", "Critical issues only".
 
@@ -177,9 +168,9 @@ Ask questions along these lines (adapt to the specific findings — do NOT ask g
 
 **Rules for questions**:
 - Every question must reference specific findings from Phase 2 — never ask generic "who is your audience?" questions
-- Keep it to 2-4 questions maximum — respect the user's time
+- Keep it to 2–4 questions maximum — respect the user's time
 - Offer concrete options, not open-ended prompts
-- If findings are straightforward (e.g., only 1-2 clear issues), skip questions and go directly to Phase 4
+- If findings are straightforward (e.g., only 1–2 clear issues), skip questions and go directly to Phase 4
 
 ## Phase 4: Recommended Actions
 

.agents/skills/critique/reference/personas.md

@@ -88,30 +88,30 @@ Test the interface through the eyes of 5 distinct user archetypes. Each persona
 
 ---
 
-## 4. Skeptical Evaluator — "Riley"
+## 4. Deliberate Stress Tester — "Riley"
 
-**Profile**: Evaluating the product for their team or company. Looking for reasons to reject. Comparing against competitors.
+**Profile**: Methodical user who pushes interfaces beyond the happy path. Tests edge cases, tries unexpected inputs, and probes for gaps in the experience.
 
 **Behaviors**:
 - Tests edge cases intentionally (empty states, long strings, special characters)
-- Looks for pricing catches and hidden limitations
-- Reads fine print and terms of service
-- Tries to break things deliberately
+- Submits forms with unexpected data (emoji, RTL text, very long values)
+- Tries to break workflows by navigating backwards, refreshing mid-flow, or opening in multiple tabs
+- Looks for inconsistencies between what the UI promises and what actually happens
 - Documents problems methodically
 
 **Test Questions**:
 - What happens at the edges (0 items, 1000 items, very long text)?
-- Is pricing and value proposition transparent?
-- Are there hidden limitations or gotchas?
-- How polished is error handling?
-- What data is collected and why?
+- Do error states recover gracefully or leave the UI in a broken state?
+- What happens on refresh mid-workflow? Is state preserved?
+- Are there features that appear to work but produce broken results?
+- How does the UI handle unexpected input (emoji, special chars, paste from Excel)?
 
 **Red Flags** (report these specifically):
-- Hidden pricing or "contact sales" for basic information
-- Features that appear to work but produce broken results
-- Poor error handling that exposes technical details
-- Unclear data practices or missing privacy information
+- Features that appear to work but silently fail or produce wrong results
+- Error handling that exposes technical details or leaves UI in a broken state
 - Empty states that show nothing useful ("No results" with no guidance)
+- Workflows that lose user data on refresh or navigation
+- Inconsistent behavior between similar interactions in different parts of the UI
 
 ---
 
@@ -150,7 +150,7 @@ Choose personas based on the interface type:
 |---------------|-----------------|-----|
 | Landing page / marketing | Jordan, Riley, Casey | First impressions, trust, mobile |
 | Dashboard / admin | Alex, Sam | Power users, accessibility |
-| E-commerce / checkout | Casey, Riley, Jordan | Mobile, trust, clarity |
+| E-commerce / checkout | Casey, Riley, Jordan | Mobile, edge cases, clarity |
 | Onboarding flow | Jordan, Casey | Confusion, interruption |
 | Data-heavy / analytics | Alex, Sam | Efficiency, keyboard nav |
 | Form-heavy / wizard | Jordan, Sam, Casey | Clarity, accessibility, mobile |

.claude/skills/audit/SKILL.md

@@ -1,17 +1,23 @@
 ---
 name: audit
-description: Perform a comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates a scored report with severity ratings and actionable plan. Use when the user wants a design review, accessibility check, quality audit, or a full list of UI issues to fix.
+description: Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
 user-invocable: true
 argument-hint: "[area (feature, page, component...)]"
 ---
 
-Run systematic quality checks and generate a comprehensive audit report with quantitative scoring, prioritized issues, and an actionable plan. Don't fix issues — document them for other commands to address.
+## MANDATORY PREPARATION
 
-**First**: Invoke /frontend-design for design principles and anti-patterns.
+Invoke /frontend-design — it contains design principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no design context exists yet, you MUST run /teach-impeccable first.
+
+---
+
+Run systematic **technical** quality checks and generate a comprehensive report. Don't fix issues — document them for other commands to address.
+
+This is a code-level audit, not a design critique. Check what's measurable and verifiable in the implementation.
 
 ## Diagnostic Scan
 
-Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using the criteria below.
+Run comprehensive checks across 5 dimensions. Score each dimension 0-4 using the criteria below.
 
 ### 1. Accessibility (A11y)
 
@@ -23,7 +29,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Alt text**: Missing or poor image descriptions
 - **Form issues**: Inputs without labels, poor error messaging, missing required indicators
 
-**Score 0–4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
+**Score 0-4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
 
 ### 2. Performance
 
@@ -34,7 +40,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Bundle size**: Unnecessary imports, unused dependencies
 - **Render performance**: Unnecessary re-renders, missing memoization
 
-**Score 0–4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
+**Score 0-4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
 
 ### 3. Theming
 
@@ -44,7 +50,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Inconsistent tokens**: Using wrong tokens, mixing token types
 - **Theme switching issues**: Values that don't update on theme change
 
-**Score 0–4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
+**Score 0-4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
 
 ### 4. Responsive Design
 
@@ -55,113 +61,73 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Text scaling**: Layouts that break when text size increases
 - **Missing breakpoints**: No mobile/tablet variants
 
-**Score 0–4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
+**Score 0-4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
 
 ### 5. Anti-Patterns (CRITICAL)
 
 Check against ALL the **DON'T** guidelines in the frontend-design skill. Look for AI slop tells (AI color palette, gradient text, glassmorphism, hero metrics, card grids, generic fonts) and general design anti-patterns (gray on color, nested cards, bounce easing, redundant copy).
 
-**Score 0–4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
+**Score 0-4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
 
-**CRITICAL**: This is an audit, not a fix. Document issues thoroughly with clear explanations of impact. Use other commands to fix issues after audit.
-
-## Generate Comprehensive Report
+## Generate Report
 
 ### Audit Health Score
 
-Present the dimension scores as a table:
-
 | # | Dimension | Score | Key Finding |
 |---|-----------|-------|-------------|
-| 1 | Accessibility | ? | [most critical a11y issue or "—"] |
+| 1 | Accessibility | ? | [most critical a11y issue or "--"] |
 | 2 | Performance | ? | |
 | 3 | Responsive Design | ? | |
 | 4 | Theming | ? | |
 | 5 | Anti-Patterns | ? | |
 | **Total** | | **??/20** | **[Rating band]** |
 
-**Rating bands**:
-| Score | Rating | Action |
-|-------|--------|--------|
-| 18–20 | Excellent | Minor polish only |
-| 14–17 | Good | Address weak dimensions |
-| 10–13 | Acceptable | Significant work needed |
-| 6–9 | Poor | Major quality overhaul |
-| 0–5 | Critical | Fundamental issues across the board |
+**Rating bands**: 18-20 Excellent (minor polish), 14-17 Good (address weak dimensions), 10-13 Acceptable (significant work needed), 6-9 Poor (major overhaul), 0-5 Critical (fundamental issues)
 
 ### Anti-Patterns Verdict
-**Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
+**Start here.** Pass/fail: Does this look AI-generated? List specific tells. Be brutally honest.
 
 ### Executive Summary
 - Audit Health Score: **??/20** ([rating band])
 - Total issues found (count by severity: P0/P1/P2/P3)
-- Most critical issues (top 3-5)
+- Top 3-5 critical issues
 - Recommended next steps
 
 ### Detailed Findings by Severity
 
-Tag every issue with **P0–P3 severity**:
-| Priority | Name | Description |
-|----------|------|-------------|
-| **P0** | Blocking | Prevents task completion — fix immediately |
-| **P1** | Major | Significant difficulty or WCAG AA violation — fix before release |
-| **P2** | Minor | Annoyance, workaround exists — fix in next pass |
-| **P3** | Polish | Nice-to-fix, no real user impact — fix if time permits |
+Tag every issue with **P0-P3 severity**:
+- **P0 Blocking**: Prevents task completion — fix immediately
+- **P1 Major**: Significant difficulty or WCAG AA violation — fix before release
+- **P2 Minor**: Annoyance, workaround exists — fix in next pass
+- **P3 Polish**: Nice-to-fix, no real user impact — fix if time permits
 
 For each issue, document:
 - **[P?] Issue name**
-- **Location**: Where it occurs (component, file, line)
+- **Location**: Component, file, line
 - **Category**: Accessibility / Performance / Theming / Responsive / Anti-Pattern
-- **Description**: What the issue is
 - **Impact**: How it affects users
 - **WCAG/Standard**: Which standard it violates (if applicable)
 - **Recommendation**: How to fix it
-- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive — or other installed skills you're sure exist)
-
-#### P0 — Blocking Issues
-[Issues that prevent task completion or violate WCAG A]
-
-#### P1 — Major Issues
-[Significant usability/accessibility impact, WCAG AA violations]
-
-#### P2 — Minor Issues
-[Quality issues, WCAG AAA violations, performance concerns]
-
-#### P3 — Polish Issues
-[Minor inconsistencies, optimization opportunities]
+- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Patterns & Systemic Issues
 
-Identify recurring problems:
+Identify recurring problems that indicate systemic gaps rather than one-off mistakes:
 - "Hard-coded colors appear in 15+ components, should use design tokens"
 - "Touch targets consistently too small (<44px) throughout mobile experience"
-- "Missing focus indicators on all custom interactive components"
 
 ### Positive Findings
 
-Note what's working well:
-- Good practices to maintain
-- Exemplary implementations to replicate elsewhere
+Note what's working well — good practices to maintain and replicate.
 
 ## Recommended Actions
 
-Present a prioritized action summary. Order is determined by severity automatically (P0 first, then P1, then P2).
-
-### Action Summary
-
-List recommended commands in priority order:
+List recommended commands in priority order (P0 first, then P1, then P2):
 
 1. **[P?] `/command-name`** — Brief description (specific context from audit findings)
 2. **[P?] `/command-name`** — Brief description (specific context)
-...
 
-**Rules for recommendations**:
-- Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive
-- Order by severity: P0 issues first, then P1, then P2 (skip P3 unless user has few issues)
-- Each item's description should carry enough context that the command knows what to focus on
-- Map findings to the most appropriate command
-- Skip commands that would address zero issues
-- End with `/polish` as the final step if any fixes were recommended
+**Rules**: Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive. Map findings to the most appropriate command. End with `/polish` as the final step if any fixes were recommended.
 
 After presenting the summary, tell the user:
 
@@ -173,10 +139,9 @@ After presenting the summary, tell the user:
 
 **NEVER**:
 - Report issues without explaining impact (why does this matter?)
-- Mix severity levels inconsistently
-- Skip positive findings (celebrate what works)
 - Provide generic recommendations (be specific and actionable)
+- Skip positive findings (celebrate what works)
 - Forget to prioritize (everything can't be P0)
 - Report false positives without verification
 
-Remember: You're a quality auditor with exceptional attention to detail. Document systematically, prioritize ruthlessly, and provide clear paths to improvement. A good audit makes fixing easy.
+Remember: You're a technical quality auditor. Document systematically, prioritize ruthlessly, cite specific code locations, and provide clear paths to improvement.

.claude/skills/critique/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: critique
-description: Evaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, cognitive load, and overall design quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design, UI, or component.
+description: Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
 user-invocable: true
 argument-hint: "[area (feature, page, component...)]"
 ---
@@ -11,7 +11,7 @@ Invoke /frontend-design — it contains design principles, anti-patterns, and th
 
 ---
 
-Conduct a holistic design critique, evaluating whether the interface actually works—not just technically, but as a designed experience. Think like a design director giving feedback.
+Conduct a holistic design critique, evaluating whether the interface actually works — not just technically, but as a designed experience. Think like a design director giving feedback.
 
 ## Phase 1: Design Critique
 
@@ -21,7 +21,7 @@ Evaluate the interface across these dimensions:
 
 **This is the most important check.** Does this look like every other AI-generated interface from 2024-2025?
 
-Review the design against ALL the **DON'T** guidelines in the frontend-design skill—they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
+Review the design against ALL the **DON'T** guidelines in the frontend-design skill — they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
 
 **The test**: If you showed this to someone and said "AI made this," would they believe you immediately? If yes, that's the problem.
 
@@ -31,20 +31,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Do size, color, and position communicate importance correctly?
 - Is there visual competition between elements that should have different weights?
 
-### 3. Information Architecture
-→ *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and checklist*
+### 3. Information Architecture & Cognitive Load
+> *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and 8-item checklist*
 - Is the structure intuitive? Would a new user understand the organization?
 - Is related content grouped logically?
 - Are there too many choices at once? Count visible options at each decision point — if >4, flag it
 - Is the navigation clear and predictable?
 - **Progressive disclosure**: Is complexity revealed only when needed, or dumped on the user upfront?
-- **Cognitive load sub-check**: Run the 8-item cognitive load checklist from the reference. Report the number of failures.
+- **Run the 8-item cognitive load checklist** from the reference. Report failure count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
 
 ### 4. Emotional Journey
-→ *Consult [cognitive-load](reference/cognitive-load.md) for emotional intervention patterns*
 - What emotion does this interface evoke? Is that intentional?
 - Does it match the brand personality?
-- Does it feel trustworthy, approachable, premium, playful—whatever it should feel?
+- Does it feel trustworthy, approachable, premium, playful — whatever it should feel?
 - Would the target user feel "this is for me"?
 - **Peak-end rule**: Is the most intense moment positive? Does the experience end well (confirmation, celebration, clear next step)?
 - **Emotional valleys**: Check for onboarding frustration, error cliffs, feature discovery gaps, or anxiety spikes at high-stakes moments (payment, delete, commit)
@@ -72,7 +71,7 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Is color used to communicate, not just decorate?
 - Does the palette feel cohesive?
 - Are accent colors drawing attention to the right things?
-- Does it work for colorblind users? (not just technically—does meaning still come through?)
+- Does it work for colorblind users? (not just technically — does meaning still come through?)
 
 ### 9. States & Edge Cases
 - Empty states: Do they guide users toward action, or just say "nothing here"?
@@ -86,27 +85,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Are labels and buttons unambiguous?
 - Does error copy help users fix the problem?
 
-### 11. Cognitive Load
-→ *Consult [cognitive-load](reference/cognitive-load.md)*
-- **Intrinsic vs. extraneous**: Is the mental effort coming from the task itself (acceptable) or from poor design choices (eliminate)?
-- **Decision points**: Count visible choices at key moments. More than 4 simultaneous options = overload.
-- **Working memory burden**: Does the user need to remember information from a previous screen to act on the current one?
-- **Information chunking**: Is content broken into digestible groups, or presented as undifferentiated walls?
-- Run the 8-item cognitive load checklist. Report failures count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
-
 ## Phase 2: Present Findings
 
 Structure your feedback as a design director would:
 
 ### Design Health Score
-→ *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
+> *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
 
 Score each of Nielsen's 10 heuristics 0–4. Present as a table:
 
 | # | Heuristic | Score | Key Issue |
 |---|-----------|-------|-----------|
 | 1 | Visibility of System Status | ? | [specific finding or "—" if solid] |
-| 2 | Match System ↔ Real World | ? | |
+| 2 | Match System / Real World | ? | |
 | 3 | User Control and Freedom | ? | |
 | 4 | Consistency and Standards | ? | |
 | 5 | Error Prevention | ? | |
@@ -123,13 +114,13 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score
 **Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
 
 ### Overall Impression
-A brief gut reaction—what works, what doesn't, and the single biggest opportunity.
+A brief gut reaction — what works, what doesn't, and the single biggest opportunity.
 
 ### What's Working
-Highlight 2-3 things done well. Be specific about why they work.
+Highlight 2–3 things done well. Be specific about why they work.
 
 ### Priority Issues
-The 3-5 most impactful design problems, ordered by importance.
+The 3–5 most impactful design problems, ordered by importance.
 
 For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](reference/heuristics-scoring.md) for severity definitions):
 - **[P?] What**: Name the problem clearly
@@ -138,7 +129,7 @@ For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](refe
 - **Suggested command**: Which command could address this (from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Persona Red Flags
-→ *Consult [personas](reference/personas.md)*
+> *Consult [personas](reference/personas.md)*
 
 Auto-select 2–3 personas most relevant to this interface type (use the selection table in the reference). If `CLAUDE.md` contains a `## Design Context` section from `teach-impeccable`, also generate 1–2 project-specific personas from the audience/brand info.
 
@@ -154,12 +145,12 @@ Be specific — name the exact elements and interactions that fail each persona.
 Quick notes on smaller issues worth addressing.
 
 **Remember**:
-- Be direct—vague feedback wastes everyone's time
-- Be specific—"the submit button" not "some elements"
+- Be direct — vague feedback wastes everyone's time
+- Be specific — "the submit button" not "some elements"
 - Say what's wrong AND why it matters to users
 - Give concrete suggestions, not just "consider exploring..."
-- Prioritize ruthlessly—if everything is important, nothing is
-- Don't soften criticism—developers need honest feedback to ship great design
+- Prioritize ruthlessly — if everything is important, nothing is
+- Don't soften criticism — developers need honest feedback to ship great design
 
 ## Phase 3: Ask the User
 
@@ -167,9 +158,9 @@ Quick notes on smaller issues worth addressing.
 
 Ask questions along these lines (adapt to the specific findings — do NOT ask generic questions):
 
-1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2-3 issue categories as options.
+1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2–3 issue categories as options.
 
-2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2-3 tonal directions as options based on what would fix the issues found.
+2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2–3 tonal directions as options based on what would fix the issues found.
 
 3. **Scope**: Ask how much the user wants to take on. For example: "I found N issues. Want to address everything, or focus on the top 3?" Offer scope options like "Top 3 only", "All issues", "Critical issues only".
 
@@ -177,9 +168,9 @@ Ask questions along these lines (adapt to the specific findings — do NOT ask g
 
 **Rules for questions**:
 - Every question must reference specific findings from Phase 2 — never ask generic "who is your audience?" questions
-- Keep it to 2-4 questions maximum — respect the user's time
+- Keep it to 2–4 questions maximum — respect the user's time
 - Offer concrete options, not open-ended prompts
-- If findings are straightforward (e.g., only 1-2 clear issues), skip questions and go directly to Phase 4
+- If findings are straightforward (e.g., only 1–2 clear issues), skip questions and go directly to Phase 4
 
 ## Phase 4: Recommended Actions
 

.claude/skills/critique/reference/personas.md

@@ -88,30 +88,30 @@ Test the interface through the eyes of 5 distinct user archetypes. Each persona
 
 ---
 
-## 4. Skeptical Evaluator — "Riley"
+## 4. Deliberate Stress Tester — "Riley"
 
-**Profile**: Evaluating the product for their team or company. Looking for reasons to reject. Comparing against competitors.
+**Profile**: Methodical user who pushes interfaces beyond the happy path. Tests edge cases, tries unexpected inputs, and probes for gaps in the experience.
 
 **Behaviors**:
 - Tests edge cases intentionally (empty states, long strings, special characters)
-- Looks for pricing catches and hidden limitations
-- Reads fine print and terms of service
-- Tries to break things deliberately
+- Submits forms with unexpected data (emoji, RTL text, very long values)
+- Tries to break workflows by navigating backwards, refreshing mid-flow, or opening in multiple tabs
+- Looks for inconsistencies between what the UI promises and what actually happens
 - Documents problems methodically
 
 **Test Questions**:
 - What happens at the edges (0 items, 1000 items, very long text)?
-- Is pricing and value proposition transparent?
-- Are there hidden limitations or gotchas?
-- How polished is error handling?
-- What data is collected and why?
+- Do error states recover gracefully or leave the UI in a broken state?
+- What happens on refresh mid-workflow? Is state preserved?
+- Are there features that appear to work but produce broken results?
+- How does the UI handle unexpected input (emoji, special chars, paste from Excel)?
 
 **Red Flags** (report these specifically):
-- Hidden pricing or "contact sales" for basic information
-- Features that appear to work but produce broken results
-- Poor error handling that exposes technical details
-- Unclear data practices or missing privacy information
+- Features that appear to work but silently fail or produce wrong results
+- Error handling that exposes technical details or leaves UI in a broken state
 - Empty states that show nothing useful ("No results" with no guidance)
+- Workflows that lose user data on refresh or navigation
+- Inconsistent behavior between similar interactions in different parts of the UI
 
 ---
 
@@ -150,7 +150,7 @@ Choose personas based on the interface type:
 |---------------|-----------------|-----|
 | Landing page / marketing | Jordan, Riley, Casey | First impressions, trust, mobile |
 | Dashboard / admin | Alex, Sam | Power users, accessibility |
-| E-commerce / checkout | Casey, Riley, Jordan | Mobile, trust, clarity |
+| E-commerce / checkout | Casey, Riley, Jordan | Mobile, edge cases, clarity |
 | Onboarding flow | Jordan, Casey | Confusion, interruption |
 | Data-heavy / analytics | Alex, Sam | Efficiency, keyboard nav |
 | Form-heavy / wizard | Jordan, Sam, Casey | Clarity, accessibility, mobile |

.codex/skills/audit/SKILL.md

@@ -1,16 +1,22 @@
 ---
 name: audit
-description: Perform a comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates a scored report with severity ratings and actionable plan. Use when the user wants a design review, accessibility check, quality audit, or a full list of UI issues to fix.
+description: Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
 argument-hint: "[area (feature, page, component...)]"
 ---
 
-Run systematic quality checks and generate a comprehensive audit report with quantitative scoring, prioritized issues, and an actionable plan. Don't fix issues — document them for other commands to address.
+## MANDATORY PREPARATION
 
-**First**: Invoke $frontend-design for design principles and anti-patterns.
+Invoke $frontend-design — it contains design principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no design context exists yet, you MUST run $teach-impeccable first.
+
+---
+
+Run systematic **technical** quality checks and generate a comprehensive report. Don't fix issues — document them for other commands to address.
+
+This is a code-level audit, not a design critique. Check what's measurable and verifiable in the implementation.
 
 ## Diagnostic Scan
 
-Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using the criteria below.
+Run comprehensive checks across 5 dimensions. Score each dimension 0-4 using the criteria below.
 
 ### 1. Accessibility (A11y)
 
@@ -22,7 +28,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Alt text**: Missing or poor image descriptions
 - **Form issues**: Inputs without labels, poor error messaging, missing required indicators
 
-**Score 0–4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
+**Score 0-4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
 
 ### 2. Performance
 
@@ -33,7 +39,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Bundle size**: Unnecessary imports, unused dependencies
 - **Render performance**: Unnecessary re-renders, missing memoization
 
-**Score 0–4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
+**Score 0-4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
 
 ### 3. Theming
 
@@ -43,7 +49,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Inconsistent tokens**: Using wrong tokens, mixing token types
 - **Theme switching issues**: Values that don't update on theme change
 
-**Score 0–4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
+**Score 0-4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
 
 ### 4. Responsive Design
 
@@ -54,113 +60,73 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Text scaling**: Layouts that break when text size increases
 - **Missing breakpoints**: No mobile/tablet variants
 
-**Score 0–4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
+**Score 0-4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
 
 ### 5. Anti-Patterns (CRITICAL)
 
 Check against ALL the **DON'T** guidelines in the frontend-design skill. Look for AI slop tells (AI color palette, gradient text, glassmorphism, hero metrics, card grids, generic fonts) and general design anti-patterns (gray on color, nested cards, bounce easing, redundant copy).
 
-**Score 0–4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
+**Score 0-4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
 
-**CRITICAL**: This is an audit, not a fix. Document issues thoroughly with clear explanations of impact. Use other commands to fix issues after audit.
-
-## Generate Comprehensive Report
+## Generate Report
 
 ### Audit Health Score
 
-Present the dimension scores as a table:
-
 | # | Dimension | Score | Key Finding |
 |---|-----------|-------|-------------|
-| 1 | Accessibility | ? | [most critical a11y issue or "—"] |
+| 1 | Accessibility | ? | [most critical a11y issue or "--"] |
 | 2 | Performance | ? | |
 | 3 | Responsive Design | ? | |
 | 4 | Theming | ? | |
 | 5 | Anti-Patterns | ? | |
 | **Total** | | **??/20** | **[Rating band]** |
 
-**Rating bands**:
-| Score | Rating | Action |
-|-------|--------|--------|
-| 18–20 | Excellent | Minor polish only |
-| 14–17 | Good | Address weak dimensions |
-| 10–13 | Acceptable | Significant work needed |
-| 6–9 | Poor | Major quality overhaul |
-| 0–5 | Critical | Fundamental issues across the board |
+**Rating bands**: 18-20 Excellent (minor polish), 14-17 Good (address weak dimensions), 10-13 Acceptable (significant work needed), 6-9 Poor (major overhaul), 0-5 Critical (fundamental issues)
 
 ### Anti-Patterns Verdict
-**Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
+**Start here.** Pass/fail: Does this look AI-generated? List specific tells. Be brutally honest.
 
 ### Executive Summary
 - Audit Health Score: **??/20** ([rating band])
 - Total issues found (count by severity: P0/P1/P2/P3)
-- Most critical issues (top 3-5)
+- Top 3-5 critical issues
 - Recommended next steps
 
 ### Detailed Findings by Severity
 
-Tag every issue with **P0–P3 severity**:
-| Priority | Name | Description |
-|----------|------|-------------|
-| **P0** | Blocking | Prevents task completion — fix immediately |
-| **P1** | Major | Significant difficulty or WCAG AA violation — fix before release |
-| **P2** | Minor | Annoyance, workaround exists — fix in next pass |
-| **P3** | Polish | Nice-to-fix, no real user impact — fix if time permits |
+Tag every issue with **P0-P3 severity**:
+- **P0 Blocking**: Prevents task completion — fix immediately
+- **P1 Major**: Significant difficulty or WCAG AA violation — fix before release
+- **P2 Minor**: Annoyance, workaround exists — fix in next pass
+- **P3 Polish**: Nice-to-fix, no real user impact — fix if time permits
 
 For each issue, document:
 - **[P?] Issue name**
-- **Location**: Where it occurs (component, file, line)
+- **Location**: Component, file, line
 - **Category**: Accessibility / Performance / Theming / Responsive / Anti-Pattern
-- **Description**: What the issue is
 - **Impact**: How it affects users
 - **WCAG/Standard**: Which standard it violates (if applicable)
 - **Recommendation**: How to fix it
-- **Suggested command**: Which command to use (prefer: $animate, $quieter, $optimize, $adapt, $clarify, $distill, $delight, $onboard, $normalize, $audit, $harden, $polish, $extract, $bolder, $arrange, $typeset, $critique, $colorize, $overdrive — or other installed skills you're sure exist)
-
-#### P0 — Blocking Issues
-[Issues that prevent task completion or violate WCAG A]
-
-#### P1 — Major Issues
-[Significant usability/accessibility impact, WCAG AA violations]
-
-#### P2 — Minor Issues
-[Quality issues, WCAG AAA violations, performance concerns]
-
-#### P3 — Polish Issues
-[Minor inconsistencies, optimization opportunities]
+- **Suggested command**: Which command to use (prefer: $animate, $quieter, $optimize, $adapt, $clarify, $distill, $delight, $onboard, $normalize, $audit, $harden, $polish, $extract, $bolder, $arrange, $typeset, $critique, $colorize, $overdrive)
 
 ### Patterns & Systemic Issues
 
-Identify recurring problems:
+Identify recurring problems that indicate systemic gaps rather than one-off mistakes:
 - "Hard-coded colors appear in 15+ components, should use design tokens"
 - "Touch targets consistently too small (<44px) throughout mobile experience"
-- "Missing focus indicators on all custom interactive components"
 
 ### Positive Findings
 
-Note what's working well:
-- Good practices to maintain
-- Exemplary implementations to replicate elsewhere
+Note what's working well — good practices to maintain and replicate.
 
 ## Recommended Actions
 
-Present a prioritized action summary. Order is determined by severity automatically (P0 first, then P1, then P2).
-
-### Action Summary
-
-List recommended commands in priority order:
+List recommended commands in priority order (P0 first, then P1, then P2):
 
 1. **[P?] `$command-name`** — Brief description (specific context from audit findings)
 2. **[P?] `$command-name`** — Brief description (specific context)
-...
 
-**Rules for recommendations**:
-- Only recommend commands from: $animate, $quieter, $optimize, $adapt, $clarify, $distill, $delight, $onboard, $normalize, $audit, $harden, $polish, $extract, $bolder, $arrange, $typeset, $critique, $colorize, $overdrive
-- Order by severity: P0 issues first, then P1, then P2 (skip P3 unless user has few issues)
-- Each item's description should carry enough context that the command knows what to focus on
-- Map findings to the most appropriate command
-- Skip commands that would address zero issues
-- End with `$polish` as the final step if any fixes were recommended
+**Rules**: Only recommend commands from: $animate, $quieter, $optimize, $adapt, $clarify, $distill, $delight, $onboard, $normalize, $audit, $harden, $polish, $extract, $bolder, $arrange, $typeset, $critique, $colorize, $overdrive. Map findings to the most appropriate command. End with `$polish` as the final step if any fixes were recommended.
 
 After presenting the summary, tell the user:
 
@@ -172,10 +138,9 @@ After presenting the summary, tell the user:
 
 **NEVER**:
 - Report issues without explaining impact (why does this matter?)
-- Mix severity levels inconsistently
-- Skip positive findings (celebrate what works)
 - Provide generic recommendations (be specific and actionable)
+- Skip positive findings (celebrate what works)
 - Forget to prioritize (everything can't be P0)
 - Report false positives without verification
 
-Remember: You're a quality auditor with exceptional attention to detail. Document systematically, prioritize ruthlessly, and provide clear paths to improvement. A good audit makes fixing easy.
+Remember: You're a technical quality auditor. Document systematically, prioritize ruthlessly, cite specific code locations, and provide clear paths to improvement.

.codex/skills/critique/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: critique
-description: Evaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, cognitive load, and overall design quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design, UI, or component.
+description: Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
 argument-hint: "[area (feature, page, component...)]"
 ---
 
@@ -10,7 +10,7 @@ Invoke $frontend-design — it contains design principles, anti-patterns, and th
 
 ---
 
-Conduct a holistic design critique, evaluating whether the interface actually works—not just technically, but as a designed experience. Think like a design director giving feedback.
+Conduct a holistic design critique, evaluating whether the interface actually works — not just technically, but as a designed experience. Think like a design director giving feedback.
 
 ## Phase 1: Design Critique
 
@@ -20,7 +20,7 @@ Evaluate the interface across these dimensions:
 
 **This is the most important check.** Does this look like every other AI-generated interface from 2024-2025?
 
-Review the design against ALL the **DON'T** guidelines in the frontend-design skill—they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
+Review the design against ALL the **DON'T** guidelines in the frontend-design skill — they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
 
 **The test**: If you showed this to someone and said "AI made this," would they believe you immediately? If yes, that's the problem.
 
@@ -30,20 +30,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Do size, color, and position communicate importance correctly?
 - Is there visual competition between elements that should have different weights?
 
-### 3. Information Architecture
-→ *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and checklist*
+### 3. Information Architecture & Cognitive Load
+> *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and 8-item checklist*
 - Is the structure intuitive? Would a new user understand the organization?
 - Is related content grouped logically?
 - Are there too many choices at once? Count visible options at each decision point — if >4, flag it
 - Is the navigation clear and predictable?
 - **Progressive disclosure**: Is complexity revealed only when needed, or dumped on the user upfront?
-- **Cognitive load sub-check**: Run the 8-item cognitive load checklist from the reference. Report the number of failures.
+- **Run the 8-item cognitive load checklist** from the reference. Report failure count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
 
 ### 4. Emotional Journey
-→ *Consult [cognitive-load](reference/cognitive-load.md) for emotional intervention patterns*
 - What emotion does this interface evoke? Is that intentional?
 - Does it match the brand personality?
-- Does it feel trustworthy, approachable, premium, playful—whatever it should feel?
+- Does it feel trustworthy, approachable, premium, playful — whatever it should feel?
 - Would the target user feel "this is for me"?
 - **Peak-end rule**: Is the most intense moment positive? Does the experience end well (confirmation, celebration, clear next step)?
 - **Emotional valleys**: Check for onboarding frustration, error cliffs, feature discovery gaps, or anxiety spikes at high-stakes moments (payment, delete, commit)
@@ -71,7 +70,7 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Is color used to communicate, not just decorate?
 - Does the palette feel cohesive?
 - Are accent colors drawing attention to the right things?
-- Does it work for colorblind users? (not just technically—does meaning still come through?)
+- Does it work for colorblind users? (not just technically — does meaning still come through?)
 
 ### 9. States & Edge Cases
 - Empty states: Do they guide users toward action, or just say "nothing here"?
@@ -85,27 +84,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Are labels and buttons unambiguous?
 - Does error copy help users fix the problem?
 
-### 11. Cognitive Load
-→ *Consult [cognitive-load](reference/cognitive-load.md)*
-- **Intrinsic vs. extraneous**: Is the mental effort coming from the task itself (acceptable) or from poor design choices (eliminate)?
-- **Decision points**: Count visible choices at key moments. More than 4 simultaneous options = overload.
-- **Working memory burden**: Does the user need to remember information from a previous screen to act on the current one?
-- **Information chunking**: Is content broken into digestible groups, or presented as undifferentiated walls?
-- Run the 8-item cognitive load checklist. Report failures count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
-
 ## Phase 2: Present Findings
 
 Structure your feedback as a design director would:
 
 ### Design Health Score
-→ *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
+> *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
 
 Score each of Nielsen's 10 heuristics 0–4. Present as a table:
 
 | # | Heuristic | Score | Key Issue |
 |---|-----------|-------|-----------|
 | 1 | Visibility of System Status | ? | [specific finding or "—" if solid] |
-| 2 | Match System ↔ Real World | ? | |
+| 2 | Match System / Real World | ? | |
 | 3 | User Control and Freedom | ? | |
 | 4 | Consistency and Standards | ? | |
 | 5 | Error Prevention | ? | |
@@ -122,13 +113,13 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score
 **Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
 
 ### Overall Impression
-A brief gut reaction—what works, what doesn't, and the single biggest opportunity.
+A brief gut reaction — what works, what doesn't, and the single biggest opportunity.
 
 ### What's Working
-Highlight 2-3 things done well. Be specific about why they work.
+Highlight 2–3 things done well. Be specific about why they work.
 
 ### Priority Issues
-The 3-5 most impactful design problems, ordered by importance.
+The 3–5 most impactful design problems, ordered by importance.
 
 For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](reference/heuristics-scoring.md) for severity definitions):
 - **[P?] What**: Name the problem clearly
@@ -137,7 +128,7 @@ For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](refe
 - **Suggested command**: Which command could address this (from: $animate, $quieter, $optimize, $adapt, $clarify, $distill, $delight, $onboard, $normalize, $audit, $harden, $polish, $extract, $bolder, $arrange, $typeset, $critique, $colorize, $overdrive)
 
 ### Persona Red Flags
-→ *Consult [personas](reference/personas.md)*
+> *Consult [personas](reference/personas.md)*
 
 Auto-select 2–3 personas most relevant to this interface type (use the selection table in the reference). If `AGENTS.md` contains a `## Design Context` section from `teach-impeccable`, also generate 1–2 project-specific personas from the audience/brand info.
 
@@ -153,12 +144,12 @@ Be specific — name the exact elements and interactions that fail each persona.
 Quick notes on smaller issues worth addressing.
 
 **Remember**:
-- Be direct—vague feedback wastes everyone's time
-- Be specific—"the submit button" not "some elements"
+- Be direct — vague feedback wastes everyone's time
+- Be specific — "the submit button" not "some elements"
 - Say what's wrong AND why it matters to users
 - Give concrete suggestions, not just "consider exploring..."
-- Prioritize ruthlessly—if everything is important, nothing is
-- Don't soften criticism—developers need honest feedback to ship great design
+- Prioritize ruthlessly — if everything is important, nothing is
+- Don't soften criticism — developers need honest feedback to ship great design
 
 ## Phase 3: Ask the User
 
@@ -166,9 +157,9 @@ Quick notes on smaller issues worth addressing.
 
 Ask questions along these lines (adapt to the specific findings — do NOT ask generic questions):
 
-1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2-3 issue categories as options.
+1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2–3 issue categories as options.
 
-2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer$bolder/more playful?" Offer 2-3 tonal directions as options based on what would fix the issues found.
+2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer$bolder/more playful?" Offer 2–3 tonal directions as options based on what would fix the issues found.
 
 3. **Scope**: Ask how much the user wants to take on. For example: "I found N issues. Want to address everything, or focus on the top 3?" Offer scope options like "Top 3 only", "All issues", "Critical issues only".
 
@@ -176,9 +167,9 @@ Ask questions along these lines (adapt to the specific findings — do NOT ask g
 
 **Rules for questions**:
 - Every question must reference specific findings from Phase 2 — never ask generic "who is your audience?" questions
-- Keep it to 2-4 questions maximum — respect the user's time
+- Keep it to 2–4 questions maximum — respect the user's time
 - Offer concrete options, not open-ended prompts
-- If findings are straightforward (e.g., only 1-2 clear issues), skip questions and go directly to Phase 4
+- If findings are straightforward (e.g., only 1–2 clear issues), skip questions and go directly to Phase 4
 
 ## Phase 4: Recommended Actions
 

.codex/skills/critique/reference/personas.md

@@ -88,30 +88,30 @@ Test the interface through the eyes of 5 distinct user archetypes. Each persona
 
 ---
 
-## 4. Skeptical Evaluator — "Riley"
+## 4. Deliberate Stress Tester — "Riley"
 
-**Profile**: Evaluating the product for their team or company. Looking for reasons to reject. Comparing against competitors.
+**Profile**: Methodical user who pushes interfaces beyond the happy path. Tests edge cases, tries unexpected inputs, and probes for gaps in the experience.
 
 **Behaviors**:
 - Tests edge cases intentionally (empty states, long strings, special characters)
-- Looks for pricing catches and hidden limitations
-- Reads fine print and terms of service
-- Tries to break things deliberately
+- Submits forms with unexpected data (emoji, RTL text, very long values)
+- Tries to break workflows by navigating backwards, refreshing mid-flow, or opening in multiple tabs
+- Looks for inconsistencies between what the UI promises and what actually happens
 - Documents problems methodically
 
 **Test Questions**:
 - What happens at the edges (0 items, 1000 items, very long text)?
-- Is pricing and value proposition transparent?
-- Are there hidden limitations or gotchas?
-- How polished is error handling?
-- What data is collected and why?
+- Do error states recover gracefully or leave the UI in a broken state?
+- What happens on refresh mid-workflow? Is state preserved?
+- Are there features that appear to work but produce broken results?
+- How does the UI handle unexpected input (emoji, special chars, paste from Excel)?
 
 **Red Flags** (report these specifically):
-- Hidden pricing or "contact sales" for basic information
-- Features that appear to work but produce broken results
-- Poor error handling that exposes technical details
-- Unclear data practices or missing privacy information
+- Features that appear to work but silently fail or produce wrong results
+- Error handling that exposes technical details or leaves UI in a broken state
 - Empty states that show nothing useful ("No results" with no guidance)
+- Workflows that lose user data on refresh or navigation
+- Inconsistent behavior between similar interactions in different parts of the UI
 
 ---
 
@@ -150,7 +150,7 @@ Choose personas based on the interface type:
 |---------------|-----------------|-----|
 | Landing page / marketing | Jordan, Riley, Casey | First impressions, trust, mobile |
 | Dashboard / admin | Alex, Sam | Power users, accessibility |
-| E-commerce / checkout | Casey, Riley, Jordan | Mobile, trust, clarity |
+| E-commerce / checkout | Casey, Riley, Jordan | Mobile, edge cases, clarity |
 | Onboarding flow | Jordan, Casey | Confusion, interruption |
 | Data-heavy / analytics | Alex, Sam | Efficiency, keyboard nav |
 | Form-heavy / wizard | Jordan, Sam, Casey | Clarity, accessibility, mobile |

.cursor/skills/audit/SKILL.md

@@ -1,15 +1,21 @@
 ---
 name: audit
-description: Perform a comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates a scored report with severity ratings and actionable plan. Use when the user wants a design review, accessibility check, quality audit, or a full list of UI issues to fix.
+description: Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
 ---
 
-Run systematic quality checks and generate a comprehensive audit report with quantitative scoring, prioritized issues, and an actionable plan. Don't fix issues — document them for other commands to address.
+## MANDATORY PREPARATION
 
-**First**: Invoke /frontend-design for design principles and anti-patterns.
+Invoke /frontend-design — it contains design principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no design context exists yet, you MUST run /teach-impeccable first.
+
+---
+
+Run systematic **technical** quality checks and generate a comprehensive report. Don't fix issues — document them for other commands to address.
+
+This is a code-level audit, not a design critique. Check what's measurable and verifiable in the implementation.
 
 ## Diagnostic Scan
 
-Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using the criteria below.
+Run comprehensive checks across 5 dimensions. Score each dimension 0-4 using the criteria below.
 
 ### 1. Accessibility (A11y)
 
@@ -21,7 +27,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Alt text**: Missing or poor image descriptions
 - **Form issues**: Inputs without labels, poor error messaging, missing required indicators
 
-**Score 0–4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
+**Score 0-4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
 
 ### 2. Performance
 
@@ -32,7 +38,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Bundle size**: Unnecessary imports, unused dependencies
 - **Render performance**: Unnecessary re-renders, missing memoization
 
-**Score 0–4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
+**Score 0-4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
 
 ### 3. Theming
 
@@ -42,7 +48,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Inconsistent tokens**: Using wrong tokens, mixing token types
 - **Theme switching issues**: Values that don't update on theme change
 
-**Score 0–4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
+**Score 0-4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
 
 ### 4. Responsive Design
 
@@ -53,113 +59,73 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Text scaling**: Layouts that break when text size increases
 - **Missing breakpoints**: No mobile/tablet variants
 
-**Score 0–4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
+**Score 0-4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
 
 ### 5. Anti-Patterns (CRITICAL)
 
 Check against ALL the **DON'T** guidelines in the frontend-design skill. Look for AI slop tells (AI color palette, gradient text, glassmorphism, hero metrics, card grids, generic fonts) and general design anti-patterns (gray on color, nested cards, bounce easing, redundant copy).
 
-**Score 0–4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
+**Score 0-4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
 
-**CRITICAL**: This is an audit, not a fix. Document issues thoroughly with clear explanations of impact. Use other commands to fix issues after audit.
-
-## Generate Comprehensive Report
+## Generate Report
 
 ### Audit Health Score
 
-Present the dimension scores as a table:
-
 | # | Dimension | Score | Key Finding |
 |---|-----------|-------|-------------|
-| 1 | Accessibility | ? | [most critical a11y issue or "—"] |
+| 1 | Accessibility | ? | [most critical a11y issue or "--"] |
 | 2 | Performance | ? | |
 | 3 | Responsive Design | ? | |
 | 4 | Theming | ? | |
 | 5 | Anti-Patterns | ? | |
 | **Total** | | **??/20** | **[Rating band]** |
 
-**Rating bands**:
-| Score | Rating | Action |
-|-------|--------|--------|
-| 18–20 | Excellent | Minor polish only |
-| 14–17 | Good | Address weak dimensions |
-| 10–13 | Acceptable | Significant work needed |
-| 6–9 | Poor | Major quality overhaul |
-| 0–5 | Critical | Fundamental issues across the board |
+**Rating bands**: 18-20 Excellent (minor polish), 14-17 Good (address weak dimensions), 10-13 Acceptable (significant work needed), 6-9 Poor (major overhaul), 0-5 Critical (fundamental issues)
 
 ### Anti-Patterns Verdict
-**Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
+**Start here.** Pass/fail: Does this look AI-generated? List specific tells. Be brutally honest.
 
 ### Executive Summary
 - Audit Health Score: **??/20** ([rating band])
 - Total issues found (count by severity: P0/P1/P2/P3)
-- Most critical issues (top 3-5)
+- Top 3-5 critical issues
 - Recommended next steps
 
 ### Detailed Findings by Severity
 
-Tag every issue with **P0–P3 severity**:
-| Priority | Name | Description |
-|----------|------|-------------|
-| **P0** | Blocking | Prevents task completion — fix immediately |
-| **P1** | Major | Significant difficulty or WCAG AA violation — fix before release |
-| **P2** | Minor | Annoyance, workaround exists — fix in next pass |
-| **P3** | Polish | Nice-to-fix, no real user impact — fix if time permits |
+Tag every issue with **P0-P3 severity**:
+- **P0 Blocking**: Prevents task completion — fix immediately
+- **P1 Major**: Significant difficulty or WCAG AA violation — fix before release
+- **P2 Minor**: Annoyance, workaround exists — fix in next pass
+- **P3 Polish**: Nice-to-fix, no real user impact — fix if time permits
 
 For each issue, document:
 - **[P?] Issue name**
-- **Location**: Where it occurs (component, file, line)
+- **Location**: Component, file, line
 - **Category**: Accessibility / Performance / Theming / Responsive / Anti-Pattern
-- **Description**: What the issue is
 - **Impact**: How it affects users
 - **WCAG/Standard**: Which standard it violates (if applicable)
 - **Recommendation**: How to fix it
-- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive — or other installed skills you're sure exist)
-
-#### P0 — Blocking Issues
-[Issues that prevent task completion or violate WCAG A]
-
-#### P1 — Major Issues
-[Significant usability/accessibility impact, WCAG AA violations]
-
-#### P2 — Minor Issues
-[Quality issues, WCAG AAA violations, performance concerns]
-
-#### P3 — Polish Issues
-[Minor inconsistencies, optimization opportunities]
+- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Patterns & Systemic Issues
 
-Identify recurring problems:
+Identify recurring problems that indicate systemic gaps rather than one-off mistakes:
 - "Hard-coded colors appear in 15+ components, should use design tokens"
 - "Touch targets consistently too small (<44px) throughout mobile experience"
-- "Missing focus indicators on all custom interactive components"
 
 ### Positive Findings
 
-Note what's working well:
-- Good practices to maintain
-- Exemplary implementations to replicate elsewhere
+Note what's working well — good practices to maintain and replicate.
 
 ## Recommended Actions
 
-Present a prioritized action summary. Order is determined by severity automatically (P0 first, then P1, then P2).
-
-### Action Summary
-
-List recommended commands in priority order:
+List recommended commands in priority order (P0 first, then P1, then P2):
 
 1. **[P?] `/command-name`** — Brief description (specific context from audit findings)
 2. **[P?] `/command-name`** — Brief description (specific context)
-...
 
-**Rules for recommendations**:
-- Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive
-- Order by severity: P0 issues first, then P1, then P2 (skip P3 unless user has few issues)
-- Each item's description should carry enough context that the command knows what to focus on
-- Map findings to the most appropriate command
-- Skip commands that would address zero issues
-- End with `/polish` as the final step if any fixes were recommended
+**Rules**: Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive. Map findings to the most appropriate command. End with `/polish` as the final step if any fixes were recommended.
 
 After presenting the summary, tell the user:
 
@@ -171,10 +137,9 @@ After presenting the summary, tell the user:
 
 **NEVER**:
 - Report issues without explaining impact (why does this matter?)
-- Mix severity levels inconsistently
-- Skip positive findings (celebrate what works)
 - Provide generic recommendations (be specific and actionable)
+- Skip positive findings (celebrate what works)
 - Forget to prioritize (everything can't be P0)
 - Report false positives without verification
 
-Remember: You're a quality auditor with exceptional attention to detail. Document systematically, prioritize ruthlessly, and provide clear paths to improvement. A good audit makes fixing easy.
+Remember: You're a technical quality auditor. Document systematically, prioritize ruthlessly, cite specific code locations, and provide clear paths to improvement.

.cursor/skills/critique/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: critique
-description: Evaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, cognitive load, and overall design quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design, UI, or component.
+description: Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
 ---
 
 ## MANDATORY PREPARATION
@@ -9,7 +9,7 @@ Invoke /frontend-design — it contains design principles, anti-patterns, and th
 
 ---
 
-Conduct a holistic design critique, evaluating whether the interface actually works—not just technically, but as a designed experience. Think like a design director giving feedback.
+Conduct a holistic design critique, evaluating whether the interface actually works — not just technically, but as a designed experience. Think like a design director giving feedback.
 
 ## Phase 1: Design Critique
 
@@ -19,7 +19,7 @@ Evaluate the interface across these dimensions:
 
 **This is the most important check.** Does this look like every other AI-generated interface from 2024-2025?
 
-Review the design against ALL the **DON'T** guidelines in the frontend-design skill—they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
+Review the design against ALL the **DON'T** guidelines in the frontend-design skill — they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
 
 **The test**: If you showed this to someone and said "AI made this," would they believe you immediately? If yes, that's the problem.
 
@@ -29,20 +29,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Do size, color, and position communicate importance correctly?
 - Is there visual competition between elements that should have different weights?
 
-### 3. Information Architecture
-→ *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and checklist*
+### 3. Information Architecture & Cognitive Load
+> *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and 8-item checklist*
 - Is the structure intuitive? Would a new user understand the organization?
 - Is related content grouped logically?
 - Are there too many choices at once? Count visible options at each decision point — if >4, flag it
 - Is the navigation clear and predictable?
 - **Progressive disclosure**: Is complexity revealed only when needed, or dumped on the user upfront?
-- **Cognitive load sub-check**: Run the 8-item cognitive load checklist from the reference. Report the number of failures.
+- **Run the 8-item cognitive load checklist** from the reference. Report failure count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
 
 ### 4. Emotional Journey
-→ *Consult [cognitive-load](reference/cognitive-load.md) for emotional intervention patterns*
 - What emotion does this interface evoke? Is that intentional?
 - Does it match the brand personality?
-- Does it feel trustworthy, approachable, premium, playful—whatever it should feel?
+- Does it feel trustworthy, approachable, premium, playful — whatever it should feel?
 - Would the target user feel "this is for me"?
 - **Peak-end rule**: Is the most intense moment positive? Does the experience end well (confirmation, celebration, clear next step)?
 - **Emotional valleys**: Check for onboarding frustration, error cliffs, feature discovery gaps, or anxiety spikes at high-stakes moments (payment, delete, commit)
@@ -70,7 +69,7 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Is color used to communicate, not just decorate?
 - Does the palette feel cohesive?
 - Are accent colors drawing attention to the right things?
-- Does it work for colorblind users? (not just technically—does meaning still come through?)
+- Does it work for colorblind users? (not just technically — does meaning still come through?)
 
 ### 9. States & Edge Cases
 - Empty states: Do they guide users toward action, or just say "nothing here"?
@@ -84,27 +83,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Are labels and buttons unambiguous?
 - Does error copy help users fix the problem?
 
-### 11. Cognitive Load
-→ *Consult [cognitive-load](reference/cognitive-load.md)*
-- **Intrinsic vs. extraneous**: Is the mental effort coming from the task itself (acceptable) or from poor design choices (eliminate)?
-- **Decision points**: Count visible choices at key moments. More than 4 simultaneous options = overload.
-- **Working memory burden**: Does the user need to remember information from a previous screen to act on the current one?
-- **Information chunking**: Is content broken into digestible groups, or presented as undifferentiated walls?
-- Run the 8-item cognitive load checklist. Report failures count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
-
 ## Phase 2: Present Findings
 
 Structure your feedback as a design director would:
 
 ### Design Health Score
-→ *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
+> *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
 
 Score each of Nielsen's 10 heuristics 0–4. Present as a table:
 
 | # | Heuristic | Score | Key Issue |
 |---|-----------|-------|-----------|
 | 1 | Visibility of System Status | ? | [specific finding or "—" if solid] |
-| 2 | Match System ↔ Real World | ? | |
+| 2 | Match System / Real World | ? | |
 | 3 | User Control and Freedom | ? | |
 | 4 | Consistency and Standards | ? | |
 | 5 | Error Prevention | ? | |
@@ -121,13 +112,13 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score
 **Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
 
 ### Overall Impression
-A brief gut reaction—what works, what doesn't, and the single biggest opportunity.
+A brief gut reaction — what works, what doesn't, and the single biggest opportunity.
 
 ### What's Working
-Highlight 2-3 things done well. Be specific about why they work.
+Highlight 2–3 things done well. Be specific about why they work.
 
 ### Priority Issues
-The 3-5 most impactful design problems, ordered by importance.
+The 3–5 most impactful design problems, ordered by importance.
 
 For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](reference/heuristics-scoring.md) for severity definitions):
 - **[P?] What**: Name the problem clearly
@@ -136,7 +127,7 @@ For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](refe
 - **Suggested command**: Which command could address this (from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Persona Red Flags
-→ *Consult [personas](reference/personas.md)*
+> *Consult [personas](reference/personas.md)*
 
 Auto-select 2–3 personas most relevant to this interface type (use the selection table in the reference). If `.cursorrules` contains a `## Design Context` section from `teach-impeccable`, also generate 1–2 project-specific personas from the audience/brand info.
 
@@ -152,12 +143,12 @@ Be specific — name the exact elements and interactions that fail each persona.
 Quick notes on smaller issues worth addressing.
 
 **Remember**:
-- Be direct—vague feedback wastes everyone's time
-- Be specific—"the submit button" not "some elements"
+- Be direct — vague feedback wastes everyone's time
+- Be specific — "the submit button" not "some elements"
 - Say what's wrong AND why it matters to users
 - Give concrete suggestions, not just "consider exploring..."
-- Prioritize ruthlessly—if everything is important, nothing is
-- Don't soften criticism—developers need honest feedback to ship great design
+- Prioritize ruthlessly — if everything is important, nothing is
+- Don't soften criticism — developers need honest feedback to ship great design
 
 ## Phase 3: Ask the User
 
@@ -165,9 +156,9 @@ Quick notes on smaller issues worth addressing.
 
 Ask questions along these lines (adapt to the specific findings — do NOT ask generic questions):
 
-1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2-3 issue categories as options.
+1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2–3 issue categories as options.
 
-2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2-3 tonal directions as options based on what would fix the issues found.
+2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2–3 tonal directions as options based on what would fix the issues found.
 
 3. **Scope**: Ask how much the user wants to take on. For example: "I found N issues. Want to address everything, or focus on the top 3?" Offer scope options like "Top 3 only", "All issues", "Critical issues only".
 
@@ -175,9 +166,9 @@ Ask questions along these lines (adapt to the specific findings — do NOT ask g
 
 **Rules for questions**:
 - Every question must reference specific findings from Phase 2 — never ask generic "who is your audience?" questions
-- Keep it to 2-4 questions maximum — respect the user's time
+- Keep it to 2–4 questions maximum — respect the user's time
 - Offer concrete options, not open-ended prompts
-- If findings are straightforward (e.g., only 1-2 clear issues), skip questions and go directly to Phase 4
+- If findings are straightforward (e.g., only 1–2 clear issues), skip questions and go directly to Phase 4
 
 ## Phase 4: Recommended Actions
 

.cursor/skills/critique/reference/personas.md

@@ -88,30 +88,30 @@ Test the interface through the eyes of 5 distinct user archetypes. Each persona
 
 ---
 
-## 4. Skeptical Evaluator — "Riley"
+## 4. Deliberate Stress Tester — "Riley"
 
-**Profile**: Evaluating the product for their team or company. Looking for reasons to reject. Comparing against competitors.
+**Profile**: Methodical user who pushes interfaces beyond the happy path. Tests edge cases, tries unexpected inputs, and probes for gaps in the experience.
 
 **Behaviors**:
 - Tests edge cases intentionally (empty states, long strings, special characters)
-- Looks for pricing catches and hidden limitations
-- Reads fine print and terms of service
-- Tries to break things deliberately
+- Submits forms with unexpected data (emoji, RTL text, very long values)
+- Tries to break workflows by navigating backwards, refreshing mid-flow, or opening in multiple tabs
+- Looks for inconsistencies between what the UI promises and what actually happens
 - Documents problems methodically
 
 **Test Questions**:
 - What happens at the edges (0 items, 1000 items, very long text)?
-- Is pricing and value proposition transparent?
-- Are there hidden limitations or gotchas?
-- How polished is error handling?
-- What data is collected and why?
+- Do error states recover gracefully or leave the UI in a broken state?
+- What happens on refresh mid-workflow? Is state preserved?
+- Are there features that appear to work but produce broken results?
+- How does the UI handle unexpected input (emoji, special chars, paste from Excel)?
 
 **Red Flags** (report these specifically):
-- Hidden pricing or "contact sales" for basic information
-- Features that appear to work but produce broken results
-- Poor error handling that exposes technical details
-- Unclear data practices or missing privacy information
+- Features that appear to work but silently fail or produce wrong results
+- Error handling that exposes technical details or leaves UI in a broken state
 - Empty states that show nothing useful ("No results" with no guidance)
+- Workflows that lose user data on refresh or navigation
+- Inconsistent behavior between similar interactions in different parts of the UI
 
 ---
 
@@ -150,7 +150,7 @@ Choose personas based on the interface type:
 |---------------|-----------------|-----|
 | Landing page / marketing | Jordan, Riley, Casey | First impressions, trust, mobile |
 | Dashboard / admin | Alex, Sam | Power users, accessibility |
-| E-commerce / checkout | Casey, Riley, Jordan | Mobile, trust, clarity |
+| E-commerce / checkout | Casey, Riley, Jordan | Mobile, edge cases, clarity |
 | Onboarding flow | Jordan, Casey | Confusion, interruption |
 | Data-heavy / analytics | Alex, Sam | Efficiency, keyboard nav |
 | Form-heavy / wizard | Jordan, Sam, Casey | Clarity, accessibility, mobile |

.gemini/skills/audit/SKILL.md

@@ -1,15 +1,21 @@
 ---
 name: audit
-description: Perform a comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates a scored report with severity ratings and actionable plan. Use when the user wants a design review, accessibility check, quality audit, or a full list of UI issues to fix.
+description: Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
 ---
 
-Run systematic quality checks and generate a comprehensive audit report with quantitative scoring, prioritized issues, and an actionable plan. Don't fix issues — document them for other commands to address.
+## MANDATORY PREPARATION
 
-**First**: Invoke /frontend-design for design principles and anti-patterns.
+Invoke /frontend-design — it contains design principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no design context exists yet, you MUST run /teach-impeccable first.
+
+---
+
+Run systematic **technical** quality checks and generate a comprehensive report. Don't fix issues — document them for other commands to address.
+
+This is a code-level audit, not a design critique. Check what's measurable and verifiable in the implementation.
 
 ## Diagnostic Scan
 
-Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using the criteria below.
+Run comprehensive checks across 5 dimensions. Score each dimension 0-4 using the criteria below.
 
 ### 1. Accessibility (A11y)
 
@@ -21,7 +27,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Alt text**: Missing or poor image descriptions
 - **Form issues**: Inputs without labels, poor error messaging, missing required indicators
 
-**Score 0–4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
+**Score 0-4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
 
 ### 2. Performance
 
@@ -32,7 +38,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Bundle size**: Unnecessary imports, unused dependencies
 - **Render performance**: Unnecessary re-renders, missing memoization
 
-**Score 0–4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
+**Score 0-4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
 
 ### 3. Theming
 
@@ -42,7 +48,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Inconsistent tokens**: Using wrong tokens, mixing token types
 - **Theme switching issues**: Values that don't update on theme change
 
-**Score 0–4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
+**Score 0-4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
 
 ### 4. Responsive Design
 
@@ -53,113 +59,73 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Text scaling**: Layouts that break when text size increases
 - **Missing breakpoints**: No mobile/tablet variants
 
-**Score 0–4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
+**Score 0-4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
 
 ### 5. Anti-Patterns (CRITICAL)
 
 Check against ALL the **DON'T** guidelines in the frontend-design skill. Look for AI slop tells (AI color palette, gradient text, glassmorphism, hero metrics, card grids, generic fonts) and general design anti-patterns (gray on color, nested cards, bounce easing, redundant copy).
 
-**Score 0–4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
+**Score 0-4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
 
-**CRITICAL**: This is an audit, not a fix. Document issues thoroughly with clear explanations of impact. Use other commands to fix issues after audit.
-
-## Generate Comprehensive Report
+## Generate Report
 
 ### Audit Health Score
 
-Present the dimension scores as a table:
-
 | # | Dimension | Score | Key Finding |
 |---|-----------|-------|-------------|
-| 1 | Accessibility | ? | [most critical a11y issue or "—"] |
+| 1 | Accessibility | ? | [most critical a11y issue or "--"] |
 | 2 | Performance | ? | |
 | 3 | Responsive Design | ? | |
 | 4 | Theming | ? | |
 | 5 | Anti-Patterns | ? | |
 | **Total** | | **??/20** | **[Rating band]** |
 
-**Rating bands**:
-| Score | Rating | Action |
-|-------|--------|--------|
-| 18–20 | Excellent | Minor polish only |
-| 14–17 | Good | Address weak dimensions |
-| 10–13 | Acceptable | Significant work needed |
-| 6–9 | Poor | Major quality overhaul |
-| 0–5 | Critical | Fundamental issues across the board |
+**Rating bands**: 18-20 Excellent (minor polish), 14-17 Good (address weak dimensions), 10-13 Acceptable (significant work needed), 6-9 Poor (major overhaul), 0-5 Critical (fundamental issues)
 
 ### Anti-Patterns Verdict
-**Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
+**Start here.** Pass/fail: Does this look AI-generated? List specific tells. Be brutally honest.
 
 ### Executive Summary
 - Audit Health Score: **??/20** ([rating band])
 - Total issues found (count by severity: P0/P1/P2/P3)
-- Most critical issues (top 3-5)
+- Top 3-5 critical issues
 - Recommended next steps
 
 ### Detailed Findings by Severity
 
-Tag every issue with **P0–P3 severity**:
-| Priority | Name | Description |
-|----------|------|-------------|
-| **P0** | Blocking | Prevents task completion — fix immediately |
-| **P1** | Major | Significant difficulty or WCAG AA violation — fix before release |
-| **P2** | Minor | Annoyance, workaround exists — fix in next pass |
-| **P3** | Polish | Nice-to-fix, no real user impact — fix if time permits |
+Tag every issue with **P0-P3 severity**:
+- **P0 Blocking**: Prevents task completion — fix immediately
+- **P1 Major**: Significant difficulty or WCAG AA violation — fix before release
+- **P2 Minor**: Annoyance, workaround exists — fix in next pass
+- **P3 Polish**: Nice-to-fix, no real user impact — fix if time permits
 
 For each issue, document:
 - **[P?] Issue name**
-- **Location**: Where it occurs (component, file, line)
+- **Location**: Component, file, line
 - **Category**: Accessibility / Performance / Theming / Responsive / Anti-Pattern
-- **Description**: What the issue is
 - **Impact**: How it affects users
 - **WCAG/Standard**: Which standard it violates (if applicable)
 - **Recommendation**: How to fix it
-- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive — or other installed skills you're sure exist)
-
-#### P0 — Blocking Issues
-[Issues that prevent task completion or violate WCAG A]
-
-#### P1 — Major Issues
-[Significant usability/accessibility impact, WCAG AA violations]
-
-#### P2 — Minor Issues
-[Quality issues, WCAG AAA violations, performance concerns]
-
-#### P3 — Polish Issues
-[Minor inconsistencies, optimization opportunities]
+- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Patterns & Systemic Issues
 
-Identify recurring problems:
+Identify recurring problems that indicate systemic gaps rather than one-off mistakes:
 - "Hard-coded colors appear in 15+ components, should use design tokens"
 - "Touch targets consistently too small (<44px) throughout mobile experience"
-- "Missing focus indicators on all custom interactive components"
 
 ### Positive Findings
 
-Note what's working well:
-- Good practices to maintain
-- Exemplary implementations to replicate elsewhere
+Note what's working well — good practices to maintain and replicate.
 
 ## Recommended Actions
 
-Present a prioritized action summary. Order is determined by severity automatically (P0 first, then P1, then P2).
-
-### Action Summary
-
-List recommended commands in priority order:
+List recommended commands in priority order (P0 first, then P1, then P2):
 
 1. **[P?] `/command-name`** — Brief description (specific context from audit findings)
 2. **[P?] `/command-name`** — Brief description (specific context)
-...
 
-**Rules for recommendations**:
-- Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive
-- Order by severity: P0 issues first, then P1, then P2 (skip P3 unless user has few issues)
-- Each item's description should carry enough context that the command knows what to focus on
-- Map findings to the most appropriate command
-- Skip commands that would address zero issues
-- End with `/polish` as the final step if any fixes were recommended
+**Rules**: Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive. Map findings to the most appropriate command. End with `/polish` as the final step if any fixes were recommended.
 
 After presenting the summary, tell the user:
 
@@ -171,10 +137,9 @@ After presenting the summary, tell the user:
 
 **NEVER**:
 - Report issues without explaining impact (why does this matter?)
-- Mix severity levels inconsistently
-- Skip positive findings (celebrate what works)
 - Provide generic recommendations (be specific and actionable)
+- Skip positive findings (celebrate what works)
 - Forget to prioritize (everything can't be P0)
 - Report false positives without verification
 
-Remember: You're a quality auditor with exceptional attention to detail. Document systematically, prioritize ruthlessly, and provide clear paths to improvement. A good audit makes fixing easy.
+Remember: You're a technical quality auditor. Document systematically, prioritize ruthlessly, cite specific code locations, and provide clear paths to improvement.

.gemini/skills/critique/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: critique
-description: Evaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, cognitive load, and overall design quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design, UI, or component.
+description: Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
 ---
 
 ## MANDATORY PREPARATION
@@ -9,7 +9,7 @@ Invoke /frontend-design — it contains design principles, anti-patterns, and th
 
 ---
 
-Conduct a holistic design critique, evaluating whether the interface actually works—not just technically, but as a designed experience. Think like a design director giving feedback.
+Conduct a holistic design critique, evaluating whether the interface actually works — not just technically, but as a designed experience. Think like a design director giving feedback.
 
 ## Phase 1: Design Critique
 
@@ -19,7 +19,7 @@ Evaluate the interface across these dimensions:
 
 **This is the most important check.** Does this look like every other AI-generated interface from 2024-2025?
 
-Review the design against ALL the **DON'T** guidelines in the frontend-design skill—they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
+Review the design against ALL the **DON'T** guidelines in the frontend-design skill — they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
 
 **The test**: If you showed this to someone and said "AI made this," would they believe you immediately? If yes, that's the problem.
 
@@ -29,20 +29,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Do size, color, and position communicate importance correctly?
 - Is there visual competition between elements that should have different weights?
 
-### 3. Information Architecture
-→ *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and checklist*
+### 3. Information Architecture & Cognitive Load
+> *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and 8-item checklist*
 - Is the structure intuitive? Would a new user understand the organization?
 - Is related content grouped logically?
 - Are there too many choices at once? Count visible options at each decision point — if >4, flag it
 - Is the navigation clear and predictable?
 - **Progressive disclosure**: Is complexity revealed only when needed, or dumped on the user upfront?
-- **Cognitive load sub-check**: Run the 8-item cognitive load checklist from the reference. Report the number of failures.
+- **Run the 8-item cognitive load checklist** from the reference. Report failure count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
 
 ### 4. Emotional Journey
-→ *Consult [cognitive-load](reference/cognitive-load.md) for emotional intervention patterns*
 - What emotion does this interface evoke? Is that intentional?
 - Does it match the brand personality?
-- Does it feel trustworthy, approachable, premium, playful—whatever it should feel?
+- Does it feel trustworthy, approachable, premium, playful — whatever it should feel?
 - Would the target user feel "this is for me"?
 - **Peak-end rule**: Is the most intense moment positive? Does the experience end well (confirmation, celebration, clear next step)?
 - **Emotional valleys**: Check for onboarding frustration, error cliffs, feature discovery gaps, or anxiety spikes at high-stakes moments (payment, delete, commit)
@@ -70,7 +69,7 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Is color used to communicate, not just decorate?
 - Does the palette feel cohesive?
 - Are accent colors drawing attention to the right things?
-- Does it work for colorblind users? (not just technically—does meaning still come through?)
+- Does it work for colorblind users? (not just technically — does meaning still come through?)
 
 ### 9. States & Edge Cases
 - Empty states: Do they guide users toward action, or just say "nothing here"?
@@ -84,27 +83,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Are labels and buttons unambiguous?
 - Does error copy help users fix the problem?
 
-### 11. Cognitive Load
-→ *Consult [cognitive-load](reference/cognitive-load.md)*
-- **Intrinsic vs. extraneous**: Is the mental effort coming from the task itself (acceptable) or from poor design choices (eliminate)?
-- **Decision points**: Count visible choices at key moments. More than 4 simultaneous options = overload.
-- **Working memory burden**: Does the user need to remember information from a previous screen to act on the current one?
-- **Information chunking**: Is content broken into digestible groups, or presented as undifferentiated walls?
-- Run the 8-item cognitive load checklist. Report failures count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
-
 ## Phase 2: Present Findings
 
 Structure your feedback as a design director would:
 
 ### Design Health Score
-→ *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
+> *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
 
 Score each of Nielsen's 10 heuristics 0–4. Present as a table:
 
 | # | Heuristic | Score | Key Issue |
 |---|-----------|-------|-----------|
 | 1 | Visibility of System Status | ? | [specific finding or "—" if solid] |
-| 2 | Match System ↔ Real World | ? | |
+| 2 | Match System / Real World | ? | |
 | 3 | User Control and Freedom | ? | |
 | 4 | Consistency and Standards | ? | |
 | 5 | Error Prevention | ? | |
@@ -121,13 +112,13 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score
 **Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
 
 ### Overall Impression
-A brief gut reaction—what works, what doesn't, and the single biggest opportunity.
+A brief gut reaction — what works, what doesn't, and the single biggest opportunity.
 
 ### What's Working
-Highlight 2-3 things done well. Be specific about why they work.
+Highlight 2–3 things done well. Be specific about why they work.
 
 ### Priority Issues
-The 3-5 most impactful design problems, ordered by importance.
+The 3–5 most impactful design problems, ordered by importance.
 
 For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](reference/heuristics-scoring.md) for severity definitions):
 - **[P?] What**: Name the problem clearly
@@ -136,7 +127,7 @@ For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](refe
 - **Suggested command**: Which command could address this (from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Persona Red Flags
-→ *Consult [personas](reference/personas.md)*
+> *Consult [personas](reference/personas.md)*
 
 Auto-select 2–3 personas most relevant to this interface type (use the selection table in the reference). If `GEMINI.md` contains a `## Design Context` section from `teach-impeccable`, also generate 1–2 project-specific personas from the audience/brand info.
 
@@ -152,12 +143,12 @@ Be specific — name the exact elements and interactions that fail each persona.
 Quick notes on smaller issues worth addressing.
 
 **Remember**:
-- Be direct—vague feedback wastes everyone's time
-- Be specific—"the submit button" not "some elements"
+- Be direct — vague feedback wastes everyone's time
+- Be specific — "the submit button" not "some elements"
 - Say what's wrong AND why it matters to users
 - Give concrete suggestions, not just "consider exploring..."
-- Prioritize ruthlessly—if everything is important, nothing is
-- Don't soften criticism—developers need honest feedback to ship great design
+- Prioritize ruthlessly — if everything is important, nothing is
+- Don't soften criticism — developers need honest feedback to ship great design
 
 ## Phase 3: Ask the User
 
@@ -165,9 +156,9 @@ Quick notes on smaller issues worth addressing.
 
 Ask questions along these lines (adapt to the specific findings — do NOT ask generic questions):
 
-1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2-3 issue categories as options.
+1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2–3 issue categories as options.
 
-2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2-3 tonal directions as options based on what would fix the issues found.
+2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2–3 tonal directions as options based on what would fix the issues found.
 
 3. **Scope**: Ask how much the user wants to take on. For example: "I found N issues. Want to address everything, or focus on the top 3?" Offer scope options like "Top 3 only", "All issues", "Critical issues only".
 
@@ -175,9 +166,9 @@ Ask questions along these lines (adapt to the specific findings — do NOT ask g
 
 **Rules for questions**:
 - Every question must reference specific findings from Phase 2 — never ask generic "who is your audience?" questions
-- Keep it to 2-4 questions maximum — respect the user's time
+- Keep it to 2–4 questions maximum — respect the user's time
 - Offer concrete options, not open-ended prompts
-- If findings are straightforward (e.g., only 1-2 clear issues), skip questions and go directly to Phase 4
+- If findings are straightforward (e.g., only 1–2 clear issues), skip questions and go directly to Phase 4
 
 ## Phase 4: Recommended Actions
 

.gemini/skills/critique/reference/personas.md

@@ -88,30 +88,30 @@ Test the interface through the eyes of 5 distinct user archetypes. Each persona
 
 ---
 
-## 4. Skeptical Evaluator — "Riley"
+## 4. Deliberate Stress Tester — "Riley"
 
-**Profile**: Evaluating the product for their team or company. Looking for reasons to reject. Comparing against competitors.
+**Profile**: Methodical user who pushes interfaces beyond the happy path. Tests edge cases, tries unexpected inputs, and probes for gaps in the experience.
 
 **Behaviors**:
 - Tests edge cases intentionally (empty states, long strings, special characters)
-- Looks for pricing catches and hidden limitations
-- Reads fine print and terms of service
-- Tries to break things deliberately
+- Submits forms with unexpected data (emoji, RTL text, very long values)
+- Tries to break workflows by navigating backwards, refreshing mid-flow, or opening in multiple tabs
+- Looks for inconsistencies between what the UI promises and what actually happens
 - Documents problems methodically
 
 **Test Questions**:
 - What happens at the edges (0 items, 1000 items, very long text)?
-- Is pricing and value proposition transparent?
-- Are there hidden limitations or gotchas?
-- How polished is error handling?
-- What data is collected and why?
+- Do error states recover gracefully or leave the UI in a broken state?
+- What happens on refresh mid-workflow? Is state preserved?
+- Are there features that appear to work but produce broken results?
+- How does the UI handle unexpected input (emoji, special chars, paste from Excel)?
 
 **Red Flags** (report these specifically):
-- Hidden pricing or "contact sales" for basic information
-- Features that appear to work but produce broken results
-- Poor error handling that exposes technical details
-- Unclear data practices or missing privacy information
+- Features that appear to work but silently fail or produce wrong results
+- Error handling that exposes technical details or leaves UI in a broken state
 - Empty states that show nothing useful ("No results" with no guidance)
+- Workflows that lose user data on refresh or navigation
+- Inconsistent behavior between similar interactions in different parts of the UI
 
 ---
 
@@ -150,7 +150,7 @@ Choose personas based on the interface type:
 |---------------|-----------------|-----|
 | Landing page / marketing | Jordan, Riley, Casey | First impressions, trust, mobile |
 | Dashboard / admin | Alex, Sam | Power users, accessibility |
-| E-commerce / checkout | Casey, Riley, Jordan | Mobile, trust, clarity |
+| E-commerce / checkout | Casey, Riley, Jordan | Mobile, edge cases, clarity |
 | Onboarding flow | Jordan, Casey | Confusion, interruption |
 | Data-heavy / analytics | Alex, Sam | Efficiency, keyboard nav |
 | Form-heavy / wizard | Jordan, Sam, Casey | Clarity, accessibility, mobile |

.kiro/skills/audit/SKILL.md

@@ -1,15 +1,21 @@
 ---
 name: audit
-description: Perform a comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates a scored report with severity ratings and actionable plan. Use when the user wants a design review, accessibility check, quality audit, or a full list of UI issues to fix.
+description: Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
 ---
 
-Run systematic quality checks and generate a comprehensive audit report with quantitative scoring, prioritized issues, and an actionable plan. Don't fix issues — document them for other commands to address.
+## MANDATORY PREPARATION
 
-**First**: Invoke /frontend-design for design principles and anti-patterns.
+Invoke /frontend-design — it contains design principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no design context exists yet, you MUST run /teach-impeccable first.
+
+---
+
+Run systematic **technical** quality checks and generate a comprehensive report. Don't fix issues — document them for other commands to address.
+
+This is a code-level audit, not a design critique. Check what's measurable and verifiable in the implementation.
 
 ## Diagnostic Scan
 
-Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using the criteria below.
+Run comprehensive checks across 5 dimensions. Score each dimension 0-4 using the criteria below.
 
 ### 1. Accessibility (A11y)
 
@@ -21,7 +27,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Alt text**: Missing or poor image descriptions
 - **Form issues**: Inputs without labels, poor error messaging, missing required indicators
 
-**Score 0–4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
+**Score 0-4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
 
 ### 2. Performance
 
@@ -32,7 +38,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Bundle size**: Unnecessary imports, unused dependencies
 - **Render performance**: Unnecessary re-renders, missing memoization
 
-**Score 0–4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
+**Score 0-4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
 
 ### 3. Theming
 
@@ -42,7 +48,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Inconsistent tokens**: Using wrong tokens, mixing token types
 - **Theme switching issues**: Values that don't update on theme change
 
-**Score 0–4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
+**Score 0-4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
 
 ### 4. Responsive Design
 
@@ -53,113 +59,73 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Text scaling**: Layouts that break when text size increases
 - **Missing breakpoints**: No mobile/tablet variants
 
-**Score 0–4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
+**Score 0-4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
 
 ### 5. Anti-Patterns (CRITICAL)
 
 Check against ALL the **DON'T** guidelines in the frontend-design skill. Look for AI slop tells (AI color palette, gradient text, glassmorphism, hero metrics, card grids, generic fonts) and general design anti-patterns (gray on color, nested cards, bounce easing, redundant copy).
 
-**Score 0–4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
+**Score 0-4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
 
-**CRITICAL**: This is an audit, not a fix. Document issues thoroughly with clear explanations of impact. Use other commands to fix issues after audit.
-
-## Generate Comprehensive Report
+## Generate Report
 
 ### Audit Health Score
 
-Present the dimension scores as a table:
-
 | # | Dimension | Score | Key Finding |
 |---|-----------|-------|-------------|
-| 1 | Accessibility | ? | [most critical a11y issue or "—"] |
+| 1 | Accessibility | ? | [most critical a11y issue or "--"] |
 | 2 | Performance | ? | |
 | 3 | Responsive Design | ? | |
 | 4 | Theming | ? | |
 | 5 | Anti-Patterns | ? | |
 | **Total** | | **??/20** | **[Rating band]** |
 
-**Rating bands**:
-| Score | Rating | Action |
-|-------|--------|--------|
-| 18–20 | Excellent | Minor polish only |
-| 14–17 | Good | Address weak dimensions |
-| 10–13 | Acceptable | Significant work needed |
-| 6–9 | Poor | Major quality overhaul |
-| 0–5 | Critical | Fundamental issues across the board |
+**Rating bands**: 18-20 Excellent (minor polish), 14-17 Good (address weak dimensions), 10-13 Acceptable (significant work needed), 6-9 Poor (major overhaul), 0-5 Critical (fundamental issues)
 
 ### Anti-Patterns Verdict
-**Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
+**Start here.** Pass/fail: Does this look AI-generated? List specific tells. Be brutally honest.
 
 ### Executive Summary
 - Audit Health Score: **??/20** ([rating band])
 - Total issues found (count by severity: P0/P1/P2/P3)
-- Most critical issues (top 3-5)
+- Top 3-5 critical issues
 - Recommended next steps
 
 ### Detailed Findings by Severity
 
-Tag every issue with **P0–P3 severity**:
-| Priority | Name | Description |
-|----------|------|-------------|
-| **P0** | Blocking | Prevents task completion — fix immediately |
-| **P1** | Major | Significant difficulty or WCAG AA violation — fix before release |
-| **P2** | Minor | Annoyance, workaround exists — fix in next pass |
-| **P3** | Polish | Nice-to-fix, no real user impact — fix if time permits |
+Tag every issue with **P0-P3 severity**:
+- **P0 Blocking**: Prevents task completion — fix immediately
+- **P1 Major**: Significant difficulty or WCAG AA violation — fix before release
+- **P2 Minor**: Annoyance, workaround exists — fix in next pass
+- **P3 Polish**: Nice-to-fix, no real user impact — fix if time permits
 
 For each issue, document:
 - **[P?] Issue name**
-- **Location**: Where it occurs (component, file, line)
+- **Location**: Component, file, line
 - **Category**: Accessibility / Performance / Theming / Responsive / Anti-Pattern
-- **Description**: What the issue is
 - **Impact**: How it affects users
 - **WCAG/Standard**: Which standard it violates (if applicable)
 - **Recommendation**: How to fix it
-- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive — or other installed skills you're sure exist)
-
-#### P0 — Blocking Issues
-[Issues that prevent task completion or violate WCAG A]
-
-#### P1 — Major Issues
-[Significant usability/accessibility impact, WCAG AA violations]
-
-#### P2 — Minor Issues
-[Quality issues, WCAG AAA violations, performance concerns]
-
-#### P3 — Polish Issues
-[Minor inconsistencies, optimization opportunities]
+- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Patterns & Systemic Issues
 
-Identify recurring problems:
+Identify recurring problems that indicate systemic gaps rather than one-off mistakes:
 - "Hard-coded colors appear in 15+ components, should use design tokens"
 - "Touch targets consistently too small (<44px) throughout mobile experience"
-- "Missing focus indicators on all custom interactive components"
 
 ### Positive Findings
 
-Note what's working well:
-- Good practices to maintain
-- Exemplary implementations to replicate elsewhere
+Note what's working well — good practices to maintain and replicate.
 
 ## Recommended Actions
 
-Present a prioritized action summary. Order is determined by severity automatically (P0 first, then P1, then P2).
-
-### Action Summary
-
-List recommended commands in priority order:
+List recommended commands in priority order (P0 first, then P1, then P2):
 
 1. **[P?] `/command-name`** — Brief description (specific context from audit findings)
 2. **[P?] `/command-name`** — Brief description (specific context)
-...
 
-**Rules for recommendations**:
-- Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive
-- Order by severity: P0 issues first, then P1, then P2 (skip P3 unless user has few issues)
-- Each item's description should carry enough context that the command knows what to focus on
-- Map findings to the most appropriate command
-- Skip commands that would address zero issues
-- End with `/polish` as the final step if any fixes were recommended
+**Rules**: Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive. Map findings to the most appropriate command. End with `/polish` as the final step if any fixes were recommended.
 
 After presenting the summary, tell the user:
 
@@ -171,10 +137,9 @@ After presenting the summary, tell the user:
 
 **NEVER**:
 - Report issues without explaining impact (why does this matter?)
-- Mix severity levels inconsistently
-- Skip positive findings (celebrate what works)
 - Provide generic recommendations (be specific and actionable)
+- Skip positive findings (celebrate what works)
 - Forget to prioritize (everything can't be P0)
 - Report false positives without verification
 
-Remember: You're a quality auditor with exceptional attention to detail. Document systematically, prioritize ruthlessly, and provide clear paths to improvement. A good audit makes fixing easy.
+Remember: You're a technical quality auditor. Document systematically, prioritize ruthlessly, cite specific code locations, and provide clear paths to improvement.

.kiro/skills/critique/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: critique
-description: Evaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, cognitive load, and overall design quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design, UI, or component.
+description: Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
 ---
 
 ## MANDATORY PREPARATION
@@ -9,7 +9,7 @@ Invoke /frontend-design — it contains design principles, anti-patterns, and th
 
 ---
 
-Conduct a holistic design critique, evaluating whether the interface actually works—not just technically, but as a designed experience. Think like a design director giving feedback.
+Conduct a holistic design critique, evaluating whether the interface actually works — not just technically, but as a designed experience. Think like a design director giving feedback.
 
 ## Phase 1: Design Critique
 
@@ -19,7 +19,7 @@ Evaluate the interface across these dimensions:
 
 **This is the most important check.** Does this look like every other AI-generated interface from 2024-2025?
 
-Review the design against ALL the **DON'T** guidelines in the frontend-design skill—they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
+Review the design against ALL the **DON'T** guidelines in the frontend-design skill — they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
 
 **The test**: If you showed this to someone and said "AI made this," would they believe you immediately? If yes, that's the problem.
 
@@ -29,20 +29,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Do size, color, and position communicate importance correctly?
 - Is there visual competition between elements that should have different weights?
 
-### 3. Information Architecture
-→ *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and checklist*
+### 3. Information Architecture & Cognitive Load
+> *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and 8-item checklist*
 - Is the structure intuitive? Would a new user understand the organization?
 - Is related content grouped logically?
 - Are there too many choices at once? Count visible options at each decision point — if >4, flag it
 - Is the navigation clear and predictable?
 - **Progressive disclosure**: Is complexity revealed only when needed, or dumped on the user upfront?
-- **Cognitive load sub-check**: Run the 8-item cognitive load checklist from the reference. Report the number of failures.
+- **Run the 8-item cognitive load checklist** from the reference. Report failure count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
 
 ### 4. Emotional Journey
-→ *Consult [cognitive-load](reference/cognitive-load.md) for emotional intervention patterns*
 - What emotion does this interface evoke? Is that intentional?
 - Does it match the brand personality?
-- Does it feel trustworthy, approachable, premium, playful—whatever it should feel?
+- Does it feel trustworthy, approachable, premium, playful — whatever it should feel?
 - Would the target user feel "this is for me"?
 - **Peak-end rule**: Is the most intense moment positive? Does the experience end well (confirmation, celebration, clear next step)?
 - **Emotional valleys**: Check for onboarding frustration, error cliffs, feature discovery gaps, or anxiety spikes at high-stakes moments (payment, delete, commit)
@@ -70,7 +69,7 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Is color used to communicate, not just decorate?
 - Does the palette feel cohesive?
 - Are accent colors drawing attention to the right things?
-- Does it work for colorblind users? (not just technically—does meaning still come through?)
+- Does it work for colorblind users? (not just technically — does meaning still come through?)
 
 ### 9. States & Edge Cases
 - Empty states: Do they guide users toward action, or just say "nothing here"?
@@ -84,27 +83,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Are labels and buttons unambiguous?
 - Does error copy help users fix the problem?
 
-### 11. Cognitive Load
-→ *Consult [cognitive-load](reference/cognitive-load.md)*
-- **Intrinsic vs. extraneous**: Is the mental effort coming from the task itself (acceptable) or from poor design choices (eliminate)?
-- **Decision points**: Count visible choices at key moments. More than 4 simultaneous options = overload.
-- **Working memory burden**: Does the user need to remember information from a previous screen to act on the current one?
-- **Information chunking**: Is content broken into digestible groups, or presented as undifferentiated walls?
-- Run the 8-item cognitive load checklist. Report failures count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
-
 ## Phase 2: Present Findings
 
 Structure your feedback as a design director would:
 
 ### Design Health Score
-→ *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
+> *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
 
 Score each of Nielsen's 10 heuristics 0–4. Present as a table:
 
 | # | Heuristic | Score | Key Issue |
 |---|-----------|-------|-----------|
 | 1 | Visibility of System Status | ? | [specific finding or "—" if solid] |
-| 2 | Match System ↔ Real World | ? | |
+| 2 | Match System / Real World | ? | |
 | 3 | User Control and Freedom | ? | |
 | 4 | Consistency and Standards | ? | |
 | 5 | Error Prevention | ? | |
@@ -121,13 +112,13 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score
 **Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
 
 ### Overall Impression
-A brief gut reaction—what works, what doesn't, and the single biggest opportunity.
+A brief gut reaction — what works, what doesn't, and the single biggest opportunity.
 
 ### What's Working
-Highlight 2-3 things done well. Be specific about why they work.
+Highlight 2–3 things done well. Be specific about why they work.
 
 ### Priority Issues
-The 3-5 most impactful design problems, ordered by importance.
+The 3–5 most impactful design problems, ordered by importance.
 
 For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](reference/heuristics-scoring.md) for severity definitions):
 - **[P?] What**: Name the problem clearly
@@ -136,7 +127,7 @@ For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](refe
 - **Suggested command**: Which command could address this (from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Persona Red Flags
-→ *Consult [personas](reference/personas.md)*
+> *Consult [personas](reference/personas.md)*
 
 Auto-select 2–3 personas most relevant to this interface type (use the selection table in the reference). If `.kiro/settings.json` contains a `## Design Context` section from `teach-impeccable`, also generate 1–2 project-specific personas from the audience/brand info.
 
@@ -152,12 +143,12 @@ Be specific — name the exact elements and interactions that fail each persona.
 Quick notes on smaller issues worth addressing.
 
 **Remember**:
-- Be direct—vague feedback wastes everyone's time
-- Be specific—"the submit button" not "some elements"
+- Be direct — vague feedback wastes everyone's time
+- Be specific — "the submit button" not "some elements"
 - Say what's wrong AND why it matters to users
 - Give concrete suggestions, not just "consider exploring..."
-- Prioritize ruthlessly—if everything is important, nothing is
-- Don't soften criticism—developers need honest feedback to ship great design
+- Prioritize ruthlessly — if everything is important, nothing is
+- Don't soften criticism — developers need honest feedback to ship great design
 
 ## Phase 3: Ask the User
 
@@ -165,9 +156,9 @@ Quick notes on smaller issues worth addressing.
 
 Ask questions along these lines (adapt to the specific findings — do NOT ask generic questions):
 
-1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2-3 issue categories as options.
+1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2–3 issue categories as options.
 
-2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2-3 tonal directions as options based on what would fix the issues found.
+2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2–3 tonal directions as options based on what would fix the issues found.
 
 3. **Scope**: Ask how much the user wants to take on. For example: "I found N issues. Want to address everything, or focus on the top 3?" Offer scope options like "Top 3 only", "All issues", "Critical issues only".
 
@@ -175,9 +166,9 @@ Ask questions along these lines (adapt to the specific findings — do NOT ask g
 
 **Rules for questions**:
 - Every question must reference specific findings from Phase 2 — never ask generic "who is your audience?" questions
-- Keep it to 2-4 questions maximum — respect the user's time
+- Keep it to 2–4 questions maximum — respect the user's time
 - Offer concrete options, not open-ended prompts
-- If findings are straightforward (e.g., only 1-2 clear issues), skip questions and go directly to Phase 4
+- If findings are straightforward (e.g., only 1–2 clear issues), skip questions and go directly to Phase 4
 
 ## Phase 4: Recommended Actions
 

.kiro/skills/critique/reference/personas.md

@@ -88,30 +88,30 @@ Test the interface through the eyes of 5 distinct user archetypes. Each persona
 
 ---
 
-## 4. Skeptical Evaluator — "Riley"
+## 4. Deliberate Stress Tester — "Riley"
 
-**Profile**: Evaluating the product for their team or company. Looking for reasons to reject. Comparing against competitors.
+**Profile**: Methodical user who pushes interfaces beyond the happy path. Tests edge cases, tries unexpected inputs, and probes for gaps in the experience.
 
 **Behaviors**:
 - Tests edge cases intentionally (empty states, long strings, special characters)
-- Looks for pricing catches and hidden limitations
-- Reads fine print and terms of service
-- Tries to break things deliberately
+- Submits forms with unexpected data (emoji, RTL text, very long values)
+- Tries to break workflows by navigating backwards, refreshing mid-flow, or opening in multiple tabs
+- Looks for inconsistencies between what the UI promises and what actually happens
 - Documents problems methodically
 
 **Test Questions**:
 - What happens at the edges (0 items, 1000 items, very long text)?
-- Is pricing and value proposition transparent?
-- Are there hidden limitations or gotchas?
-- How polished is error handling?
-- What data is collected and why?
+- Do error states recover gracefully or leave the UI in a broken state?
+- What happens on refresh mid-workflow? Is state preserved?
+- Are there features that appear to work but produce broken results?
+- How does the UI handle unexpected input (emoji, special chars, paste from Excel)?
 
 **Red Flags** (report these specifically):
-- Hidden pricing or "contact sales" for basic information
-- Features that appear to work but produce broken results
-- Poor error handling that exposes technical details
-- Unclear data practices or missing privacy information
+- Features that appear to work but silently fail or produce wrong results
+- Error handling that exposes technical details or leaves UI in a broken state
 - Empty states that show nothing useful ("No results" with no guidance)
+- Workflows that lose user data on refresh or navigation
+- Inconsistent behavior between similar interactions in different parts of the UI
 
 ---
 
@@ -150,7 +150,7 @@ Choose personas based on the interface type:
 |---------------|-----------------|-----|
 | Landing page / marketing | Jordan, Riley, Casey | First impressions, trust, mobile |
 | Dashboard / admin | Alex, Sam | Power users, accessibility |
-| E-commerce / checkout | Casey, Riley, Jordan | Mobile, trust, clarity |
+| E-commerce / checkout | Casey, Riley, Jordan | Mobile, edge cases, clarity |
 | Onboarding flow | Jordan, Casey | Confusion, interruption |
 | Data-heavy / analytics | Alex, Sam | Efficiency, keyboard nav |
 | Form-heavy / wizard | Jordan, Sam, Casey | Clarity, accessibility, mobile |

.opencode/skills/audit/SKILL.md

@@ -1,17 +1,23 @@
 ---
 name: audit
-description: Perform a comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates a scored report with severity ratings and actionable plan. Use when the user wants a design review, accessibility check, quality audit, or a full list of UI issues to fix.
+description: Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
 user-invocable: true
 argument-hint: "[area (feature, page, component...)]"
 ---
 
-Run systematic quality checks and generate a comprehensive audit report with quantitative scoring, prioritized issues, and an actionable plan. Don't fix issues — document them for other commands to address.
+## MANDATORY PREPARATION
 
-**First**: Invoke /frontend-design for design principles and anti-patterns.
+Invoke /frontend-design — it contains design principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no design context exists yet, you MUST run /teach-impeccable first.
+
+---
+
+Run systematic **technical** quality checks and generate a comprehensive report. Don't fix issues — document them for other commands to address.
+
+This is a code-level audit, not a design critique. Check what's measurable and verifiable in the implementation.
 
 ## Diagnostic Scan
 
-Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using the criteria below.
+Run comprehensive checks across 5 dimensions. Score each dimension 0-4 using the criteria below.
 
 ### 1. Accessibility (A11y)
 
@@ -23,7 +29,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Alt text**: Missing or poor image descriptions
 - **Form issues**: Inputs without labels, poor error messaging, missing required indicators
 
-**Score 0–4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
+**Score 0-4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
 
 ### 2. Performance
 
@@ -34,7 +40,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Bundle size**: Unnecessary imports, unused dependencies
 - **Render performance**: Unnecessary re-renders, missing memoization
 
-**Score 0–4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
+**Score 0-4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
 
 ### 3. Theming
 
@@ -44,7 +50,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Inconsistent tokens**: Using wrong tokens, mixing token types
 - **Theme switching issues**: Values that don't update on theme change
 
-**Score 0–4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
+**Score 0-4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
 
 ### 4. Responsive Design
 
@@ -55,113 +61,73 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Text scaling**: Layouts that break when text size increases
 - **Missing breakpoints**: No mobile/tablet variants
 
-**Score 0–4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
+**Score 0-4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
 
 ### 5. Anti-Patterns (CRITICAL)
 
 Check against ALL the **DON'T** guidelines in the frontend-design skill. Look for AI slop tells (AI color palette, gradient text, glassmorphism, hero metrics, card grids, generic fonts) and general design anti-patterns (gray on color, nested cards, bounce easing, redundant copy).
 
-**Score 0–4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
+**Score 0-4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
 
-**CRITICAL**: This is an audit, not a fix. Document issues thoroughly with clear explanations of impact. Use other commands to fix issues after audit.
-
-## Generate Comprehensive Report
+## Generate Report
 
 ### Audit Health Score
 
-Present the dimension scores as a table:
-
 | # | Dimension | Score | Key Finding |
 |---|-----------|-------|-------------|
-| 1 | Accessibility | ? | [most critical a11y issue or "—"] |
+| 1 | Accessibility | ? | [most critical a11y issue or "--"] |
 | 2 | Performance | ? | |
 | 3 | Responsive Design | ? | |
 | 4 | Theming | ? | |
 | 5 | Anti-Patterns | ? | |
 | **Total** | | **??/20** | **[Rating band]** |
 
-**Rating bands**:
-| Score | Rating | Action |
-|-------|--------|--------|
-| 18–20 | Excellent | Minor polish only |
-| 14–17 | Good | Address weak dimensions |
-| 10–13 | Acceptable | Significant work needed |
-| 6–9 | Poor | Major quality overhaul |
-| 0–5 | Critical | Fundamental issues across the board |
+**Rating bands**: 18-20 Excellent (minor polish), 14-17 Good (address weak dimensions), 10-13 Acceptable (significant work needed), 6-9 Poor (major overhaul), 0-5 Critical (fundamental issues)
 
 ### Anti-Patterns Verdict
-**Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
+**Start here.** Pass/fail: Does this look AI-generated? List specific tells. Be brutally honest.
 
 ### Executive Summary
 - Audit Health Score: **??/20** ([rating band])
 - Total issues found (count by severity: P0/P1/P2/P3)
-- Most critical issues (top 3-5)
+- Top 3-5 critical issues
 - Recommended next steps
 
 ### Detailed Findings by Severity
 
-Tag every issue with **P0–P3 severity**:
-| Priority | Name | Description |
-|----------|------|-------------|
-| **P0** | Blocking | Prevents task completion — fix immediately |
-| **P1** | Major | Significant difficulty or WCAG AA violation — fix before release |
-| **P2** | Minor | Annoyance, workaround exists — fix in next pass |
-| **P3** | Polish | Nice-to-fix, no real user impact — fix if time permits |
+Tag every issue with **P0-P3 severity**:
+- **P0 Blocking**: Prevents task completion — fix immediately
+- **P1 Major**: Significant difficulty or WCAG AA violation — fix before release
+- **P2 Minor**: Annoyance, workaround exists — fix in next pass
+- **P3 Polish**: Nice-to-fix, no real user impact — fix if time permits
 
 For each issue, document:
 - **[P?] Issue name**
-- **Location**: Where it occurs (component, file, line)
+- **Location**: Component, file, line
 - **Category**: Accessibility / Performance / Theming / Responsive / Anti-Pattern
-- **Description**: What the issue is
 - **Impact**: How it affects users
 - **WCAG/Standard**: Which standard it violates (if applicable)
 - **Recommendation**: How to fix it
-- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive — or other installed skills you're sure exist)
-
-#### P0 — Blocking Issues
-[Issues that prevent task completion or violate WCAG A]
-
-#### P1 — Major Issues
-[Significant usability/accessibility impact, WCAG AA violations]
-
-#### P2 — Minor Issues
-[Quality issues, WCAG AAA violations, performance concerns]
-
-#### P3 — Polish Issues
-[Minor inconsistencies, optimization opportunities]
+- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Patterns & Systemic Issues
 
-Identify recurring problems:
+Identify recurring problems that indicate systemic gaps rather than one-off mistakes:
 - "Hard-coded colors appear in 15+ components, should use design tokens"
 - "Touch targets consistently too small (<44px) throughout mobile experience"
-- "Missing focus indicators on all custom interactive components"
 
 ### Positive Findings
 
-Note what's working well:
-- Good practices to maintain
-- Exemplary implementations to replicate elsewhere
+Note what's working well — good practices to maintain and replicate.
 
 ## Recommended Actions
 
-Present a prioritized action summary. Order is determined by severity automatically (P0 first, then P1, then P2).
-
-### Action Summary
-
-List recommended commands in priority order:
+List recommended commands in priority order (P0 first, then P1, then P2):
 
 1. **[P?] `/command-name`** — Brief description (specific context from audit findings)
 2. **[P?] `/command-name`** — Brief description (specific context)
-...
 
-**Rules for recommendations**:
-- Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive
-- Order by severity: P0 issues first, then P1, then P2 (skip P3 unless user has few issues)
-- Each item's description should carry enough context that the command knows what to focus on
-- Map findings to the most appropriate command
-- Skip commands that would address zero issues
-- End with `/polish` as the final step if any fixes were recommended
+**Rules**: Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive. Map findings to the most appropriate command. End with `/polish` as the final step if any fixes were recommended.
 
 After presenting the summary, tell the user:
 
@@ -173,10 +139,9 @@ After presenting the summary, tell the user:
 
 **NEVER**:
 - Report issues without explaining impact (why does this matter?)
-- Mix severity levels inconsistently
-- Skip positive findings (celebrate what works)
 - Provide generic recommendations (be specific and actionable)
+- Skip positive findings (celebrate what works)
 - Forget to prioritize (everything can't be P0)
 - Report false positives without verification
 
-Remember: You're a quality auditor with exceptional attention to detail. Document systematically, prioritize ruthlessly, and provide clear paths to improvement. A good audit makes fixing easy.
+Remember: You're a technical quality auditor. Document systematically, prioritize ruthlessly, cite specific code locations, and provide clear paths to improvement.

.opencode/skills/critique/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: critique
-description: Evaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, cognitive load, and overall design quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design, UI, or component.
+description: Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
 user-invocable: true
 argument-hint: "[area (feature, page, component...)]"
 ---
@@ -11,7 +11,7 @@ Invoke /frontend-design — it contains design principles, anti-patterns, and th
 
 ---
 
-Conduct a holistic design critique, evaluating whether the interface actually works—not just technically, but as a designed experience. Think like a design director giving feedback.
+Conduct a holistic design critique, evaluating whether the interface actually works — not just technically, but as a designed experience. Think like a design director giving feedback.
 
 ## Phase 1: Design Critique
 
@@ -21,7 +21,7 @@ Evaluate the interface across these dimensions:
 
 **This is the most important check.** Does this look like every other AI-generated interface from 2024-2025?
 
-Review the design against ALL the **DON'T** guidelines in the frontend-design skill—they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
+Review the design against ALL the **DON'T** guidelines in the frontend-design skill — they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
 
 **The test**: If you showed this to someone and said "AI made this," would they believe you immediately? If yes, that's the problem.
 
@@ -31,20 +31,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Do size, color, and position communicate importance correctly?
 - Is there visual competition between elements that should have different weights?
 
-### 3. Information Architecture
-→ *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and checklist*
+### 3. Information Architecture & Cognitive Load
+> *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and 8-item checklist*
 - Is the structure intuitive? Would a new user understand the organization?
 - Is related content grouped logically?
 - Are there too many choices at once? Count visible options at each decision point — if >4, flag it
 - Is the navigation clear and predictable?
 - **Progressive disclosure**: Is complexity revealed only when needed, or dumped on the user upfront?
-- **Cognitive load sub-check**: Run the 8-item cognitive load checklist from the reference. Report the number of failures.
+- **Run the 8-item cognitive load checklist** from the reference. Report failure count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
 
 ### 4. Emotional Journey
-→ *Consult [cognitive-load](reference/cognitive-load.md) for emotional intervention patterns*
 - What emotion does this interface evoke? Is that intentional?
 - Does it match the brand personality?
-- Does it feel trustworthy, approachable, premium, playful—whatever it should feel?
+- Does it feel trustworthy, approachable, premium, playful — whatever it should feel?
 - Would the target user feel "this is for me"?
 - **Peak-end rule**: Is the most intense moment positive? Does the experience end well (confirmation, celebration, clear next step)?
 - **Emotional valleys**: Check for onboarding frustration, error cliffs, feature discovery gaps, or anxiety spikes at high-stakes moments (payment, delete, commit)
@@ -72,7 +71,7 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Is color used to communicate, not just decorate?
 - Does the palette feel cohesive?
 - Are accent colors drawing attention to the right things?
-- Does it work for colorblind users? (not just technically—does meaning still come through?)
+- Does it work for colorblind users? (not just technically — does meaning still come through?)
 
 ### 9. States & Edge Cases
 - Empty states: Do they guide users toward action, or just say "nothing here"?
@@ -86,27 +85,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Are labels and buttons unambiguous?
 - Does error copy help users fix the problem?
 
-### 11. Cognitive Load
-→ *Consult [cognitive-load](reference/cognitive-load.md)*
-- **Intrinsic vs. extraneous**: Is the mental effort coming from the task itself (acceptable) or from poor design choices (eliminate)?
-- **Decision points**: Count visible choices at key moments. More than 4 simultaneous options = overload.
-- **Working memory burden**: Does the user need to remember information from a previous screen to act on the current one?
-- **Information chunking**: Is content broken into digestible groups, or presented as undifferentiated walls?
-- Run the 8-item cognitive load checklist. Report failures count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
-
 ## Phase 2: Present Findings
 
 Structure your feedback as a design director would:
 
 ### Design Health Score
-→ *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
+> *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
 
 Score each of Nielsen's 10 heuristics 0–4. Present as a table:
 
 | # | Heuristic | Score | Key Issue |
 |---|-----------|-------|-----------|
 | 1 | Visibility of System Status | ? | [specific finding or "—" if solid] |
-| 2 | Match System ↔ Real World | ? | |
+| 2 | Match System / Real World | ? | |
 | 3 | User Control and Freedom | ? | |
 | 4 | Consistency and Standards | ? | |
 | 5 | Error Prevention | ? | |
@@ -123,13 +114,13 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score
 **Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
 
 ### Overall Impression
-A brief gut reaction—what works, what doesn't, and the single biggest opportunity.
+A brief gut reaction — what works, what doesn't, and the single biggest opportunity.
 
 ### What's Working
-Highlight 2-3 things done well. Be specific about why they work.
+Highlight 2–3 things done well. Be specific about why they work.
 
 ### Priority Issues
-The 3-5 most impactful design problems, ordered by importance.
+The 3–5 most impactful design problems, ordered by importance.
 
 For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](reference/heuristics-scoring.md) for severity definitions):
 - **[P?] What**: Name the problem clearly
@@ -138,7 +129,7 @@ For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](refe
 - **Suggested command**: Which command could address this (from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Persona Red Flags
-→ *Consult [personas](reference/personas.md)*
+> *Consult [personas](reference/personas.md)*
 
 Auto-select 2–3 personas most relevant to this interface type (use the selection table in the reference). If `AGENTS.md` contains a `## Design Context` section from `teach-impeccable`, also generate 1–2 project-specific personas from the audience/brand info.
 
@@ -154,12 +145,12 @@ Be specific — name the exact elements and interactions that fail each persona.
 Quick notes on smaller issues worth addressing.
 
 **Remember**:
-- Be direct—vague feedback wastes everyone's time
-- Be specific—"the submit button" not "some elements"
+- Be direct — vague feedback wastes everyone's time
+- Be specific — "the submit button" not "some elements"
 - Say what's wrong AND why it matters to users
 - Give concrete suggestions, not just "consider exploring..."
-- Prioritize ruthlessly—if everything is important, nothing is
-- Don't soften criticism—developers need honest feedback to ship great design
+- Prioritize ruthlessly — if everything is important, nothing is
+- Don't soften criticism — developers need honest feedback to ship great design
 
 ## Phase 3: Ask the User
 
@@ -167,9 +158,9 @@ Quick notes on smaller issues worth addressing.
 
 Ask questions along these lines (adapt to the specific findings — do NOT ask generic questions):
 
-1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2-3 issue categories as options.
+1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2–3 issue categories as options.
 
-2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2-3 tonal directions as options based on what would fix the issues found.
+2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2–3 tonal directions as options based on what would fix the issues found.
 
 3. **Scope**: Ask how much the user wants to take on. For example: "I found N issues. Want to address everything, or focus on the top 3?" Offer scope options like "Top 3 only", "All issues", "Critical issues only".
 
@@ -177,9 +168,9 @@ Ask questions along these lines (adapt to the specific findings — do NOT ask g
 
 **Rules for questions**:
 - Every question must reference specific findings from Phase 2 — never ask generic "who is your audience?" questions
-- Keep it to 2-4 questions maximum — respect the user's time
+- Keep it to 2–4 questions maximum — respect the user's time
 - Offer concrete options, not open-ended prompts
-- If findings are straightforward (e.g., only 1-2 clear issues), skip questions and go directly to Phase 4
+- If findings are straightforward (e.g., only 1–2 clear issues), skip questions and go directly to Phase 4
 
 ## Phase 4: Recommended Actions
 

.opencode/skills/critique/reference/personas.md

@@ -88,30 +88,30 @@ Test the interface through the eyes of 5 distinct user archetypes. Each persona
 
 ---
 
-## 4. Skeptical Evaluator — "Riley"
+## 4. Deliberate Stress Tester — "Riley"
 
-**Profile**: Evaluating the product for their team or company. Looking for reasons to reject. Comparing against competitors.
+**Profile**: Methodical user who pushes interfaces beyond the happy path. Tests edge cases, tries unexpected inputs, and probes for gaps in the experience.
 
 **Behaviors**:
 - Tests edge cases intentionally (empty states, long strings, special characters)
-- Looks for pricing catches and hidden limitations
-- Reads fine print and terms of service
-- Tries to break things deliberately
+- Submits forms with unexpected data (emoji, RTL text, very long values)
+- Tries to break workflows by navigating backwards, refreshing mid-flow, or opening in multiple tabs
+- Looks for inconsistencies between what the UI promises and what actually happens
 - Documents problems methodically
 
 **Test Questions**:
 - What happens at the edges (0 items, 1000 items, very long text)?
-- Is pricing and value proposition transparent?
-- Are there hidden limitations or gotchas?
-- How polished is error handling?
-- What data is collected and why?
+- Do error states recover gracefully or leave the UI in a broken state?
+- What happens on refresh mid-workflow? Is state preserved?
+- Are there features that appear to work but produce broken results?
+- How does the UI handle unexpected input (emoji, special chars, paste from Excel)?
 
 **Red Flags** (report these specifically):
-- Hidden pricing or "contact sales" for basic information
-- Features that appear to work but produce broken results
-- Poor error handling that exposes technical details
-- Unclear data practices or missing privacy information
+- Features that appear to work but silently fail or produce wrong results
+- Error handling that exposes technical details or leaves UI in a broken state
 - Empty states that show nothing useful ("No results" with no guidance)
+- Workflows that lose user data on refresh or navigation
+- Inconsistent behavior between similar interactions in different parts of the UI
 
 ---
 
@@ -150,7 +150,7 @@ Choose personas based on the interface type:
 |---------------|-----------------|-----|
 | Landing page / marketing | Jordan, Riley, Casey | First impressions, trust, mobile |
 | Dashboard / admin | Alex, Sam | Power users, accessibility |
-| E-commerce / checkout | Casey, Riley, Jordan | Mobile, trust, clarity |
+| E-commerce / checkout | Casey, Riley, Jordan | Mobile, edge cases, clarity |
 | Onboarding flow | Jordan, Casey | Confusion, interruption |
 | Data-heavy / analytics | Alex, Sam | Efficiency, keyboard nav |
 | Form-heavy / wizard | Jordan, Sam, Casey | Clarity, accessibility, mobile |

.pi/skills/audit/SKILL.md

@@ -1,15 +1,21 @@
 ---
 name: audit
-description: Perform a comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates a scored report with severity ratings and actionable plan. Use when the user wants a design review, accessibility check, quality audit, or a full list of UI issues to fix.
+description: Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
 ---
 
-Run systematic quality checks and generate a comprehensive audit report with quantitative scoring, prioritized issues, and an actionable plan. Don't fix issues — document them for other commands to address.
+## MANDATORY PREPARATION
 
-**First**: Invoke /frontend-design for design principles and anti-patterns.
+Invoke /frontend-design — it contains design principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no design context exists yet, you MUST run /teach-impeccable first.
+
+---
+
+Run systematic **technical** quality checks and generate a comprehensive report. Don't fix issues — document them for other commands to address.
+
+This is a code-level audit, not a design critique. Check what's measurable and verifiable in the implementation.
 
 ## Diagnostic Scan
 
-Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using the criteria below.
+Run comprehensive checks across 5 dimensions. Score each dimension 0-4 using the criteria below.
 
 ### 1. Accessibility (A11y)
 
@@ -21,7 +27,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Alt text**: Missing or poor image descriptions
 - **Form issues**: Inputs without labels, poor error messaging, missing required indicators
 
-**Score 0–4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
+**Score 0-4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
 
 ### 2. Performance
 
@@ -32,7 +38,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Bundle size**: Unnecessary imports, unused dependencies
 - **Render performance**: Unnecessary re-renders, missing memoization
 
-**Score 0–4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
+**Score 0-4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
 
 ### 3. Theming
 
@@ -42,7 +48,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Inconsistent tokens**: Using wrong tokens, mixing token types
 - **Theme switching issues**: Values that don't update on theme change
 
-**Score 0–4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
+**Score 0-4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
 
 ### 4. Responsive Design
 
@@ -53,113 +59,73 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Text scaling**: Layouts that break when text size increases
 - **Missing breakpoints**: No mobile/tablet variants
 
-**Score 0–4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
+**Score 0-4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
 
 ### 5. Anti-Patterns (CRITICAL)
 
 Check against ALL the **DON'T** guidelines in the frontend-design skill. Look for AI slop tells (AI color palette, gradient text, glassmorphism, hero metrics, card grids, generic fonts) and general design anti-patterns (gray on color, nested cards, bounce easing, redundant copy).
 
-**Score 0–4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
+**Score 0-4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
 
-**CRITICAL**: This is an audit, not a fix. Document issues thoroughly with clear explanations of impact. Use other commands to fix issues after audit.
-
-## Generate Comprehensive Report
+## Generate Report
 
 ### Audit Health Score
 
-Present the dimension scores as a table:
-
 | # | Dimension | Score | Key Finding |
 |---|-----------|-------|-------------|
-| 1 | Accessibility | ? | [most critical a11y issue or "—"] |
+| 1 | Accessibility | ? | [most critical a11y issue or "--"] |
 | 2 | Performance | ? | |
 | 3 | Responsive Design | ? | |
 | 4 | Theming | ? | |
 | 5 | Anti-Patterns | ? | |
 | **Total** | | **??/20** | **[Rating band]** |
 
-**Rating bands**:
-| Score | Rating | Action |
-|-------|--------|--------|
-| 18–20 | Excellent | Minor polish only |
-| 14–17 | Good | Address weak dimensions |
-| 10–13 | Acceptable | Significant work needed |
-| 6–9 | Poor | Major quality overhaul |
-| 0–5 | Critical | Fundamental issues across the board |
+**Rating bands**: 18-20 Excellent (minor polish), 14-17 Good (address weak dimensions), 10-13 Acceptable (significant work needed), 6-9 Poor (major overhaul), 0-5 Critical (fundamental issues)
 
 ### Anti-Patterns Verdict
-**Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
+**Start here.** Pass/fail: Does this look AI-generated? List specific tells. Be brutally honest.
 
 ### Executive Summary
 - Audit Health Score: **??/20** ([rating band])
 - Total issues found (count by severity: P0/P1/P2/P3)
-- Most critical issues (top 3-5)
+- Top 3-5 critical issues
 - Recommended next steps
 
 ### Detailed Findings by Severity
 
-Tag every issue with **P0–P3 severity**:
-| Priority | Name | Description |
-|----------|------|-------------|
-| **P0** | Blocking | Prevents task completion — fix immediately |
-| **P1** | Major | Significant difficulty or WCAG AA violation — fix before release |
-| **P2** | Minor | Annoyance, workaround exists — fix in next pass |
-| **P3** | Polish | Nice-to-fix, no real user impact — fix if time permits |
+Tag every issue with **P0-P3 severity**:
+- **P0 Blocking**: Prevents task completion — fix immediately
+- **P1 Major**: Significant difficulty or WCAG AA violation — fix before release
+- **P2 Minor**: Annoyance, workaround exists — fix in next pass
+- **P3 Polish**: Nice-to-fix, no real user impact — fix if time permits
 
 For each issue, document:
 - **[P?] Issue name**
-- **Location**: Where it occurs (component, file, line)
+- **Location**: Component, file, line
 - **Category**: Accessibility / Performance / Theming / Responsive / Anti-Pattern
-- **Description**: What the issue is
 - **Impact**: How it affects users
 - **WCAG/Standard**: Which standard it violates (if applicable)
 - **Recommendation**: How to fix it
-- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive — or other installed skills you're sure exist)
-
-#### P0 — Blocking Issues
-[Issues that prevent task completion or violate WCAG A]
-
-#### P1 — Major Issues
-[Significant usability/accessibility impact, WCAG AA violations]
-
-#### P2 — Minor Issues
-[Quality issues, WCAG AAA violations, performance concerns]
-
-#### P3 — Polish Issues
-[Minor inconsistencies, optimization opportunities]
+- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Patterns & Systemic Issues
 
-Identify recurring problems:
+Identify recurring problems that indicate systemic gaps rather than one-off mistakes:
 - "Hard-coded colors appear in 15+ components, should use design tokens"
 - "Touch targets consistently too small (<44px) throughout mobile experience"
-- "Missing focus indicators on all custom interactive components"
 
 ### Positive Findings
 
-Note what's working well:
-- Good practices to maintain
-- Exemplary implementations to replicate elsewhere
+Note what's working well — good practices to maintain and replicate.
 
 ## Recommended Actions
 
-Present a prioritized action summary. Order is determined by severity automatically (P0 first, then P1, then P2).
-
-### Action Summary
-
-List recommended commands in priority order:
+List recommended commands in priority order (P0 first, then P1, then P2):
 
 1. **[P?] `/command-name`** — Brief description (specific context from audit findings)
 2. **[P?] `/command-name`** — Brief description (specific context)
-...
 
-**Rules for recommendations**:
-- Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive
-- Order by severity: P0 issues first, then P1, then P2 (skip P3 unless user has few issues)
-- Each item's description should carry enough context that the command knows what to focus on
-- Map findings to the most appropriate command
-- Skip commands that would address zero issues
-- End with `/polish` as the final step if any fixes were recommended
+**Rules**: Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive. Map findings to the most appropriate command. End with `/polish` as the final step if any fixes were recommended.
 
 After presenting the summary, tell the user:
 
@@ -171,10 +137,9 @@ After presenting the summary, tell the user:
 
 **NEVER**:
 - Report issues without explaining impact (why does this matter?)
-- Mix severity levels inconsistently
-- Skip positive findings (celebrate what works)
 - Provide generic recommendations (be specific and actionable)
+- Skip positive findings (celebrate what works)
 - Forget to prioritize (everything can't be P0)
 - Report false positives without verification
 
-Remember: You're a quality auditor with exceptional attention to detail. Document systematically, prioritize ruthlessly, and provide clear paths to improvement. A good audit makes fixing easy.
+Remember: You're a technical quality auditor. Document systematically, prioritize ruthlessly, cite specific code locations, and provide clear paths to improvement.

.pi/skills/critique/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: critique
-description: Evaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, cognitive load, and overall design quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design, UI, or component.
+description: Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
 ---
 
 ## MANDATORY PREPARATION
@@ -9,7 +9,7 @@ Invoke /frontend-design — it contains design principles, anti-patterns, and th
 
 ---
 
-Conduct a holistic design critique, evaluating whether the interface actually works—not just technically, but as a designed experience. Think like a design director giving feedback.
+Conduct a holistic design critique, evaluating whether the interface actually works — not just technically, but as a designed experience. Think like a design director giving feedback.
 
 ## Phase 1: Design Critique
 
@@ -19,7 +19,7 @@ Evaluate the interface across these dimensions:
 
 **This is the most important check.** Does this look like every other AI-generated interface from 2024-2025?
 
-Review the design against ALL the **DON'T** guidelines in the frontend-design skill—they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
+Review the design against ALL the **DON'T** guidelines in the frontend-design skill — they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
 
 **The test**: If you showed this to someone and said "AI made this," would they believe you immediately? If yes, that's the problem.
 
@@ -29,20 +29,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Do size, color, and position communicate importance correctly?
 - Is there visual competition between elements that should have different weights?
 
-### 3. Information Architecture
-→ *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and checklist*
+### 3. Information Architecture & Cognitive Load
+> *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and 8-item checklist*
 - Is the structure intuitive? Would a new user understand the organization?
 - Is related content grouped logically?
 - Are there too many choices at once? Count visible options at each decision point — if >4, flag it
 - Is the navigation clear and predictable?
 - **Progressive disclosure**: Is complexity revealed only when needed, or dumped on the user upfront?
-- **Cognitive load sub-check**: Run the 8-item cognitive load checklist from the reference. Report the number of failures.
+- **Run the 8-item cognitive load checklist** from the reference. Report failure count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
 
 ### 4. Emotional Journey
-→ *Consult [cognitive-load](reference/cognitive-load.md) for emotional intervention patterns*
 - What emotion does this interface evoke? Is that intentional?
 - Does it match the brand personality?
-- Does it feel trustworthy, approachable, premium, playful—whatever it should feel?
+- Does it feel trustworthy, approachable, premium, playful — whatever it should feel?
 - Would the target user feel "this is for me"?
 - **Peak-end rule**: Is the most intense moment positive? Does the experience end well (confirmation, celebration, clear next step)?
 - **Emotional valleys**: Check for onboarding frustration, error cliffs, feature discovery gaps, or anxiety spikes at high-stakes moments (payment, delete, commit)
@@ -70,7 +69,7 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Is color used to communicate, not just decorate?
 - Does the palette feel cohesive?
 - Are accent colors drawing attention to the right things?
-- Does it work for colorblind users? (not just technically—does meaning still come through?)
+- Does it work for colorblind users? (not just technically — does meaning still come through?)
 
 ### 9. States & Edge Cases
 - Empty states: Do they guide users toward action, or just say "nothing here"?
@@ -84,27 +83,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Are labels and buttons unambiguous?
 - Does error copy help users fix the problem?
 
-### 11. Cognitive Load
-→ *Consult [cognitive-load](reference/cognitive-load.md)*
-- **Intrinsic vs. extraneous**: Is the mental effort coming from the task itself (acceptable) or from poor design choices (eliminate)?
-- **Decision points**: Count visible choices at key moments. More than 4 simultaneous options = overload.
-- **Working memory burden**: Does the user need to remember information from a previous screen to act on the current one?
-- **Information chunking**: Is content broken into digestible groups, or presented as undifferentiated walls?
-- Run the 8-item cognitive load checklist. Report failures count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
-
 ## Phase 2: Present Findings
 
 Structure your feedback as a design director would:
 
 ### Design Health Score
-→ *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
+> *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
 
 Score each of Nielsen's 10 heuristics 0–4. Present as a table:
 
 | # | Heuristic | Score | Key Issue |
 |---|-----------|-------|-----------|
 | 1 | Visibility of System Status | ? | [specific finding or "—" if solid] |
-| 2 | Match System ↔ Real World | ? | |
+| 2 | Match System / Real World | ? | |
 | 3 | User Control and Freedom | ? | |
 | 4 | Consistency and Standards | ? | |
 | 5 | Error Prevention | ? | |
@@ -121,13 +112,13 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score
 **Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
 
 ### Overall Impression
-A brief gut reaction—what works, what doesn't, and the single biggest opportunity.
+A brief gut reaction — what works, what doesn't, and the single biggest opportunity.
 
 ### What's Working
-Highlight 2-3 things done well. Be specific about why they work.
+Highlight 2–3 things done well. Be specific about why they work.
 
 ### Priority Issues
-The 3-5 most impactful design problems, ordered by importance.
+The 3–5 most impactful design problems, ordered by importance.
 
 For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](reference/heuristics-scoring.md) for severity definitions):
 - **[P?] What**: Name the problem clearly
@@ -136,7 +127,7 @@ For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](refe
 - **Suggested command**: Which command could address this (from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Persona Red Flags
-→ *Consult [personas](reference/personas.md)*
+> *Consult [personas](reference/personas.md)*
 
 Auto-select 2–3 personas most relevant to this interface type (use the selection table in the reference). If `AGENTS.md` contains a `## Design Context` section from `teach-impeccable`, also generate 1–2 project-specific personas from the audience/brand info.
 
@@ -152,12 +143,12 @@ Be specific — name the exact elements and interactions that fail each persona.
 Quick notes on smaller issues worth addressing.
 
 **Remember**:
-- Be direct—vague feedback wastes everyone's time
-- Be specific—"the submit button" not "some elements"
+- Be direct — vague feedback wastes everyone's time
+- Be specific — "the submit button" not "some elements"
 - Say what's wrong AND why it matters to users
 - Give concrete suggestions, not just "consider exploring..."
-- Prioritize ruthlessly—if everything is important, nothing is
-- Don't soften criticism—developers need honest feedback to ship great design
+- Prioritize ruthlessly — if everything is important, nothing is
+- Don't soften criticism — developers need honest feedback to ship great design
 
 ## Phase 3: Ask the User
 
@@ -165,9 +156,9 @@ Quick notes on smaller issues worth addressing.
 
 Ask questions along these lines (adapt to the specific findings — do NOT ask generic questions):
 
-1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2-3 issue categories as options.
+1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2–3 issue categories as options.
 
-2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2-3 tonal directions as options based on what would fix the issues found.
+2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2–3 tonal directions as options based on what would fix the issues found.
 
 3. **Scope**: Ask how much the user wants to take on. For example: "I found N issues. Want to address everything, or focus on the top 3?" Offer scope options like "Top 3 only", "All issues", "Critical issues only".
 
@@ -175,9 +166,9 @@ Ask questions along these lines (adapt to the specific findings — do NOT ask g
 
 **Rules for questions**:
 - Every question must reference specific findings from Phase 2 — never ask generic "who is your audience?" questions
-- Keep it to 2-4 questions maximum — respect the user's time
+- Keep it to 2–4 questions maximum — respect the user's time
 - Offer concrete options, not open-ended prompts
-- If findings are straightforward (e.g., only 1-2 clear issues), skip questions and go directly to Phase 4
+- If findings are straightforward (e.g., only 1–2 clear issues), skip questions and go directly to Phase 4
 
 ## Phase 4: Recommended Actions
 

.pi/skills/critique/reference/personas.md

@@ -88,30 +88,30 @@ Test the interface through the eyes of 5 distinct user archetypes. Each persona
 
 ---
 
-## 4. Skeptical Evaluator — "Riley"
+## 4. Deliberate Stress Tester — "Riley"
 
-**Profile**: Evaluating the product for their team or company. Looking for reasons to reject. Comparing against competitors.
+**Profile**: Methodical user who pushes interfaces beyond the happy path. Tests edge cases, tries unexpected inputs, and probes for gaps in the experience.
 
 **Behaviors**:
 - Tests edge cases intentionally (empty states, long strings, special characters)
-- Looks for pricing catches and hidden limitations
-- Reads fine print and terms of service
-- Tries to break things deliberately
+- Submits forms with unexpected data (emoji, RTL text, very long values)
+- Tries to break workflows by navigating backwards, refreshing mid-flow, or opening in multiple tabs
+- Looks for inconsistencies between what the UI promises and what actually happens
 - Documents problems methodically
 
 **Test Questions**:
 - What happens at the edges (0 items, 1000 items, very long text)?
-- Is pricing and value proposition transparent?
-- Are there hidden limitations or gotchas?
-- How polished is error handling?
-- What data is collected and why?
+- Do error states recover gracefully or leave the UI in a broken state?
+- What happens on refresh mid-workflow? Is state preserved?
+- Are there features that appear to work but produce broken results?
+- How does the UI handle unexpected input (emoji, special chars, paste from Excel)?
 
 **Red Flags** (report these specifically):
-- Hidden pricing or "contact sales" for basic information
-- Features that appear to work but produce broken results
-- Poor error handling that exposes technical details
-- Unclear data practices or missing privacy information
+- Features that appear to work but silently fail or produce wrong results
+- Error handling that exposes technical details or leaves UI in a broken state
 - Empty states that show nothing useful ("No results" with no guidance)
+- Workflows that lose user data on refresh or navigation
+- Inconsistent behavior between similar interactions in different parts of the UI
 
 ---
 
@@ -150,7 +150,7 @@ Choose personas based on the interface type:
 |---------------|-----------------|-----|
 | Landing page / marketing | Jordan, Riley, Casey | First impressions, trust, mobile |
 | Dashboard / admin | Alex, Sam | Power users, accessibility |
-| E-commerce / checkout | Casey, Riley, Jordan | Mobile, trust, clarity |
+| E-commerce / checkout | Casey, Riley, Jordan | Mobile, edge cases, clarity |
 | Onboarding flow | Jordan, Casey | Confusion, interruption |
 | Data-heavy / analytics | Alex, Sam | Efficiency, keyboard nav |
 | Form-heavy / wizard | Jordan, Sam, Casey | Clarity, accessibility, mobile |

.trae-cn/skills/audit/SKILL.md

@@ -1,17 +1,23 @@
 ---
 name: audit
-description: Perform a comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates a scored report with severity ratings and actionable plan. Use when the user wants a design review, accessibility check, quality audit, or a full list of UI issues to fix.
+description: Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
 user-invocable: true
 argument-hint: "[area (feature, page, component...)]"
 ---
 
-Run systematic quality checks and generate a comprehensive audit report with quantitative scoring, prioritized issues, and an actionable plan. Don't fix issues — document them for other commands to address.
+## MANDATORY PREPARATION
 
-**First**: Invoke /frontend-design for design principles and anti-patterns.
+Invoke /frontend-design — it contains design principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no design context exists yet, you MUST run /teach-impeccable first.
+
+---
+
+Run systematic **technical** quality checks and generate a comprehensive report. Don't fix issues — document them for other commands to address.
+
+This is a code-level audit, not a design critique. Check what's measurable and verifiable in the implementation.
 
 ## Diagnostic Scan
 
-Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using the criteria below.
+Run comprehensive checks across 5 dimensions. Score each dimension 0-4 using the criteria below.
 
 ### 1. Accessibility (A11y)
 
@@ -23,7 +29,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Alt text**: Missing or poor image descriptions
 - **Form issues**: Inputs without labels, poor error messaging, missing required indicators
 
-**Score 0–4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
+**Score 0-4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
 
 ### 2. Performance
 
@@ -34,7 +40,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Bundle size**: Unnecessary imports, unused dependencies
 - **Render performance**: Unnecessary re-renders, missing memoization
 
-**Score 0–4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
+**Score 0-4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
 
 ### 3. Theming
 
@@ -44,7 +50,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Inconsistent tokens**: Using wrong tokens, mixing token types
 - **Theme switching issues**: Values that don't update on theme change
 
-**Score 0–4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
+**Score 0-4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
 
 ### 4. Responsive Design
 
@@ -55,113 +61,73 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Text scaling**: Layouts that break when text size increases
 - **Missing breakpoints**: No mobile/tablet variants
 
-**Score 0–4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
+**Score 0-4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
 
 ### 5. Anti-Patterns (CRITICAL)
 
 Check against ALL the **DON'T** guidelines in the frontend-design skill. Look for AI slop tells (AI color palette, gradient text, glassmorphism, hero metrics, card grids, generic fonts) and general design anti-patterns (gray on color, nested cards, bounce easing, redundant copy).
 
-**Score 0–4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
+**Score 0-4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
 
-**CRITICAL**: This is an audit, not a fix. Document issues thoroughly with clear explanations of impact. Use other commands to fix issues after audit.
-
-## Generate Comprehensive Report
+## Generate Report
 
 ### Audit Health Score
 
-Present the dimension scores as a table:
-
 | # | Dimension | Score | Key Finding |
 |---|-----------|-------|-------------|
-| 1 | Accessibility | ? | [most critical a11y issue or "—"] |
+| 1 | Accessibility | ? | [most critical a11y issue or "--"] |
 | 2 | Performance | ? | |
 | 3 | Responsive Design | ? | |
 | 4 | Theming | ? | |
 | 5 | Anti-Patterns | ? | |
 | **Total** | | **??/20** | **[Rating band]** |
 
-**Rating bands**:
-| Score | Rating | Action |
-|-------|--------|--------|
-| 18–20 | Excellent | Minor polish only |
-| 14–17 | Good | Address weak dimensions |
-| 10–13 | Acceptable | Significant work needed |
-| 6–9 | Poor | Major quality overhaul |
-| 0–5 | Critical | Fundamental issues across the board |
+**Rating bands**: 18-20 Excellent (minor polish), 14-17 Good (address weak dimensions), 10-13 Acceptable (significant work needed), 6-9 Poor (major overhaul), 0-5 Critical (fundamental issues)
 
 ### Anti-Patterns Verdict
-**Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
+**Start here.** Pass/fail: Does this look AI-generated? List specific tells. Be brutally honest.
 
 ### Executive Summary
 - Audit Health Score: **??/20** ([rating band])
 - Total issues found (count by severity: P0/P1/P2/P3)
-- Most critical issues (top 3-5)
+- Top 3-5 critical issues
 - Recommended next steps
 
 ### Detailed Findings by Severity
 
-Tag every issue with **P0–P3 severity**:
-| Priority | Name | Description |
-|----------|------|-------------|
-| **P0** | Blocking | Prevents task completion — fix immediately |
-| **P1** | Major | Significant difficulty or WCAG AA violation — fix before release |
-| **P2** | Minor | Annoyance, workaround exists — fix in next pass |
-| **P3** | Polish | Nice-to-fix, no real user impact — fix if time permits |
+Tag every issue with **P0-P3 severity**:
+- **P0 Blocking**: Prevents task completion — fix immediately
+- **P1 Major**: Significant difficulty or WCAG AA violation — fix before release
+- **P2 Minor**: Annoyance, workaround exists — fix in next pass
+- **P3 Polish**: Nice-to-fix, no real user impact — fix if time permits
 
 For each issue, document:
 - **[P?] Issue name**
-- **Location**: Where it occurs (component, file, line)
+- **Location**: Component, file, line
 - **Category**: Accessibility / Performance / Theming / Responsive / Anti-Pattern
-- **Description**: What the issue is
 - **Impact**: How it affects users
 - **WCAG/Standard**: Which standard it violates (if applicable)
 - **Recommendation**: How to fix it
-- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive — or other installed skills you're sure exist)
-
-#### P0 — Blocking Issues
-[Issues that prevent task completion or violate WCAG A]
-
-#### P1 — Major Issues
-[Significant usability/accessibility impact, WCAG AA violations]
-
-#### P2 — Minor Issues
-[Quality issues, WCAG AAA violations, performance concerns]
-
-#### P3 — Polish Issues
-[Minor inconsistencies, optimization opportunities]
+- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Patterns & Systemic Issues
 
-Identify recurring problems:
+Identify recurring problems that indicate systemic gaps rather than one-off mistakes:
 - "Hard-coded colors appear in 15+ components, should use design tokens"
 - "Touch targets consistently too small (<44px) throughout mobile experience"
-- "Missing focus indicators on all custom interactive components"
 
 ### Positive Findings
 
-Note what's working well:
-- Good practices to maintain
-- Exemplary implementations to replicate elsewhere
+Note what's working well — good practices to maintain and replicate.
 
 ## Recommended Actions
 
-Present a prioritized action summary. Order is determined by severity automatically (P0 first, then P1, then P2).
-
-### Action Summary
-
-List recommended commands in priority order:
+List recommended commands in priority order (P0 first, then P1, then P2):
 
 1. **[P?] `/command-name`** — Brief description (specific context from audit findings)
 2. **[P?] `/command-name`** — Brief description (specific context)
-...
 
-**Rules for recommendations**:
-- Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive
-- Order by severity: P0 issues first, then P1, then P2 (skip P3 unless user has few issues)
-- Each item's description should carry enough context that the command knows what to focus on
-- Map findings to the most appropriate command
-- Skip commands that would address zero issues
-- End with `/polish` as the final step if any fixes were recommended
+**Rules**: Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive. Map findings to the most appropriate command. End with `/polish` as the final step if any fixes were recommended.
 
 After presenting the summary, tell the user:
 
@@ -173,10 +139,9 @@ After presenting the summary, tell the user:
 
 **NEVER**:
 - Report issues without explaining impact (why does this matter?)
-- Mix severity levels inconsistently
-- Skip positive findings (celebrate what works)
 - Provide generic recommendations (be specific and actionable)
+- Skip positive findings (celebrate what works)
 - Forget to prioritize (everything can't be P0)
 - Report false positives without verification
 
-Remember: You're a quality auditor with exceptional attention to detail. Document systematically, prioritize ruthlessly, and provide clear paths to improvement. A good audit makes fixing easy.
+Remember: You're a technical quality auditor. Document systematically, prioritize ruthlessly, cite specific code locations, and provide clear paths to improvement.

.trae-cn/skills/critique/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: critique
-description: Evaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, cognitive load, and overall design quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design, UI, or component.
+description: Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
 user-invocable: true
 argument-hint: "[area (feature, page, component...)]"
 ---
@@ -11,7 +11,7 @@ Invoke /frontend-design — it contains design principles, anti-patterns, and th
 
 ---
 
-Conduct a holistic design critique, evaluating whether the interface actually works—not just technically, but as a designed experience. Think like a design director giving feedback.
+Conduct a holistic design critique, evaluating whether the interface actually works — not just technically, but as a designed experience. Think like a design director giving feedback.
 
 ## Phase 1: Design Critique
 
@@ -21,7 +21,7 @@ Evaluate the interface across these dimensions:
 
 **This is the most important check.** Does this look like every other AI-generated interface from 2024-2025?
 
-Review the design against ALL the **DON'T** guidelines in the frontend-design skill—they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
+Review the design against ALL the **DON'T** guidelines in the frontend-design skill — they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
 
 **The test**: If you showed this to someone and said "AI made this," would they believe you immediately? If yes, that's the problem.
 
@@ -31,20 +31,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Do size, color, and position communicate importance correctly?
 - Is there visual competition between elements that should have different weights?
 
-### 3. Information Architecture
-→ *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and checklist*
+### 3. Information Architecture & Cognitive Load
+> *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and 8-item checklist*
 - Is the structure intuitive? Would a new user understand the organization?
 - Is related content grouped logically?
 - Are there too many choices at once? Count visible options at each decision point — if >4, flag it
 - Is the navigation clear and predictable?
 - **Progressive disclosure**: Is complexity revealed only when needed, or dumped on the user upfront?
-- **Cognitive load sub-check**: Run the 8-item cognitive load checklist from the reference. Report the number of failures.
+- **Run the 8-item cognitive load checklist** from the reference. Report failure count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
 
 ### 4. Emotional Journey
-→ *Consult [cognitive-load](reference/cognitive-load.md) for emotional intervention patterns*
 - What emotion does this interface evoke? Is that intentional?
 - Does it match the brand personality?
-- Does it feel trustworthy, approachable, premium, playful—whatever it should feel?
+- Does it feel trustworthy, approachable, premium, playful — whatever it should feel?
 - Would the target user feel "this is for me"?
 - **Peak-end rule**: Is the most intense moment positive? Does the experience end well (confirmation, celebration, clear next step)?
 - **Emotional valleys**: Check for onboarding frustration, error cliffs, feature discovery gaps, or anxiety spikes at high-stakes moments (payment, delete, commit)
@@ -72,7 +71,7 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Is color used to communicate, not just decorate?
 - Does the palette feel cohesive?
 - Are accent colors drawing attention to the right things?
-- Does it work for colorblind users? (not just technically—does meaning still come through?)
+- Does it work for colorblind users? (not just technically — does meaning still come through?)
 
 ### 9. States & Edge Cases
 - Empty states: Do they guide users toward action, or just say "nothing here"?
@@ -86,27 +85,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Are labels and buttons unambiguous?
 - Does error copy help users fix the problem?
 
-### 11. Cognitive Load
-→ *Consult [cognitive-load](reference/cognitive-load.md)*
-- **Intrinsic vs. extraneous**: Is the mental effort coming from the task itself (acceptable) or from poor design choices (eliminate)?
-- **Decision points**: Count visible choices at key moments. More than 4 simultaneous options = overload.
-- **Working memory burden**: Does the user need to remember information from a previous screen to act on the current one?
-- **Information chunking**: Is content broken into digestible groups, or presented as undifferentiated walls?
-- Run the 8-item cognitive load checklist. Report failures count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
-
 ## Phase 2: Present Findings
 
 Structure your feedback as a design director would:
 
 ### Design Health Score
-→ *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
+> *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
 
 Score each of Nielsen's 10 heuristics 0–4. Present as a table:
 
 | # | Heuristic | Score | Key Issue |
 |---|-----------|-------|-----------|
 | 1 | Visibility of System Status | ? | [specific finding or "—" if solid] |
-| 2 | Match System ↔ Real World | ? | |
+| 2 | Match System / Real World | ? | |
 | 3 | User Control and Freedom | ? | |
 | 4 | Consistency and Standards | ? | |
 | 5 | Error Prevention | ? | |
@@ -123,13 +114,13 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score
 **Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
 
 ### Overall Impression
-A brief gut reaction—what works, what doesn't, and the single biggest opportunity.
+A brief gut reaction — what works, what doesn't, and the single biggest opportunity.
 
 ### What's Working
-Highlight 2-3 things done well. Be specific about why they work.
+Highlight 2–3 things done well. Be specific about why they work.
 
 ### Priority Issues
-The 3-5 most impactful design problems, ordered by importance.
+The 3–5 most impactful design problems, ordered by importance.
 
 For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](reference/heuristics-scoring.md) for severity definitions):
 - **[P?] What**: Name the problem clearly
@@ -138,7 +129,7 @@ For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](refe
 - **Suggested command**: Which command could address this (from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Persona Red Flags
-→ *Consult [personas](reference/personas.md)*
+> *Consult [personas](reference/personas.md)*
 
 Auto-select 2–3 personas most relevant to this interface type (use the selection table in the reference). If `RULES.md` contains a `## Design Context` section from `teach-impeccable`, also generate 1–2 project-specific personas from the audience/brand info.
 
@@ -154,12 +145,12 @@ Be specific — name the exact elements and interactions that fail each persona.
 Quick notes on smaller issues worth addressing.
 
 **Remember**:
-- Be direct—vague feedback wastes everyone's time
-- Be specific—"the submit button" not "some elements"
+- Be direct — vague feedback wastes everyone's time
+- Be specific — "the submit button" not "some elements"
 - Say what's wrong AND why it matters to users
 - Give concrete suggestions, not just "consider exploring..."
-- Prioritize ruthlessly—if everything is important, nothing is
-- Don't soften criticism—developers need honest feedback to ship great design
+- Prioritize ruthlessly — if everything is important, nothing is
+- Don't soften criticism — developers need honest feedback to ship great design
 
 ## Phase 3: Ask the User
 
@@ -167,9 +158,9 @@ Quick notes on smaller issues worth addressing.
 
 Ask questions along these lines (adapt to the specific findings — do NOT ask generic questions):
 
-1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2-3 issue categories as options.
+1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2–3 issue categories as options.
 
-2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2-3 tonal directions as options based on what would fix the issues found.
+2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2–3 tonal directions as options based on what would fix the issues found.
 
 3. **Scope**: Ask how much the user wants to take on. For example: "I found N issues. Want to address everything, or focus on the top 3?" Offer scope options like "Top 3 only", "All issues", "Critical issues only".
 
@@ -177,9 +168,9 @@ Ask questions along these lines (adapt to the specific findings — do NOT ask g
 
 **Rules for questions**:
 - Every question must reference specific findings from Phase 2 — never ask generic "who is your audience?" questions
-- Keep it to 2-4 questions maximum — respect the user's time
+- Keep it to 2–4 questions maximum — respect the user's time
 - Offer concrete options, not open-ended prompts
-- If findings are straightforward (e.g., only 1-2 clear issues), skip questions and go directly to Phase 4
+- If findings are straightforward (e.g., only 1–2 clear issues), skip questions and go directly to Phase 4
 
 ## Phase 4: Recommended Actions
 

.trae-cn/skills/critique/reference/personas.md

@@ -88,30 +88,30 @@ Test the interface through the eyes of 5 distinct user archetypes. Each persona
 
 ---
 
-## 4. Skeptical Evaluator — "Riley"
+## 4. Deliberate Stress Tester — "Riley"
 
-**Profile**: Evaluating the product for their team or company. Looking for reasons to reject. Comparing against competitors.
+**Profile**: Methodical user who pushes interfaces beyond the happy path. Tests edge cases, tries unexpected inputs, and probes for gaps in the experience.
 
 **Behaviors**:
 - Tests edge cases intentionally (empty states, long strings, special characters)
-- Looks for pricing catches and hidden limitations
-- Reads fine print and terms of service
-- Tries to break things deliberately
+- Submits forms with unexpected data (emoji, RTL text, very long values)
+- Tries to break workflows by navigating backwards, refreshing mid-flow, or opening in multiple tabs
+- Looks for inconsistencies between what the UI promises and what actually happens
 - Documents problems methodically
 
 **Test Questions**:
 - What happens at the edges (0 items, 1000 items, very long text)?
-- Is pricing and value proposition transparent?
-- Are there hidden limitations or gotchas?
-- How polished is error handling?
-- What data is collected and why?
+- Do error states recover gracefully or leave the UI in a broken state?
+- What happens on refresh mid-workflow? Is state preserved?
+- Are there features that appear to work but produce broken results?
+- How does the UI handle unexpected input (emoji, special chars, paste from Excel)?
 
 **Red Flags** (report these specifically):
-- Hidden pricing or "contact sales" for basic information
-- Features that appear to work but produce broken results
-- Poor error handling that exposes technical details
-- Unclear data practices or missing privacy information
+- Features that appear to work but silently fail or produce wrong results
+- Error handling that exposes technical details or leaves UI in a broken state
 - Empty states that show nothing useful ("No results" with no guidance)
+- Workflows that lose user data on refresh or navigation
+- Inconsistent behavior between similar interactions in different parts of the UI
 
 ---
 
@@ -150,7 +150,7 @@ Choose personas based on the interface type:
 |---------------|-----------------|-----|
 | Landing page / marketing | Jordan, Riley, Casey | First impressions, trust, mobile |
 | Dashboard / admin | Alex, Sam | Power users, accessibility |
-| E-commerce / checkout | Casey, Riley, Jordan | Mobile, trust, clarity |
+| E-commerce / checkout | Casey, Riley, Jordan | Mobile, edge cases, clarity |
 | Onboarding flow | Jordan, Casey | Confusion, interruption |
 | Data-heavy / analytics | Alex, Sam | Efficiency, keyboard nav |
 | Form-heavy / wizard | Jordan, Sam, Casey | Clarity, accessibility, mobile |

.trae/skills/audit/SKILL.md

@@ -1,17 +1,23 @@
 ---
 name: audit
-description: Perform a comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates a scored report with severity ratings and actionable plan. Use when the user wants a design review, accessibility check, quality audit, or a full list of UI issues to fix.
+description: Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
 user-invocable: true
 argument-hint: "[area (feature, page, component...)]"
 ---
 
-Run systematic quality checks and generate a comprehensive audit report with quantitative scoring, prioritized issues, and an actionable plan. Don't fix issues — document them for other commands to address.
+## MANDATORY PREPARATION
 
-**First**: Invoke /frontend-design for design principles and anti-patterns.
+Invoke /frontend-design — it contains design principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no design context exists yet, you MUST run /teach-impeccable first.
+
+---
+
+Run systematic **technical** quality checks and generate a comprehensive report. Don't fix issues — document them for other commands to address.
+
+This is a code-level audit, not a design critique. Check what's measurable and verifiable in the implementation.
 
 ## Diagnostic Scan
 
-Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using the criteria below.
+Run comprehensive checks across 5 dimensions. Score each dimension 0-4 using the criteria below.
 
 ### 1. Accessibility (A11y)
 
@@ -23,7 +29,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Alt text**: Missing or poor image descriptions
 - **Form issues**: Inputs without labels, poor error messaging, missing required indicators
 
-**Score 0–4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
+**Score 0-4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
 
 ### 2. Performance
 
@@ -34,7 +40,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Bundle size**: Unnecessary imports, unused dependencies
 - **Render performance**: Unnecessary re-renders, missing memoization
 
-**Score 0–4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
+**Score 0-4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
 
 ### 3. Theming
 
@@ -44,7 +50,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Inconsistent tokens**: Using wrong tokens, mixing token types
 - **Theme switching issues**: Values that don't update on theme change
 
-**Score 0–4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
+**Score 0-4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
 
 ### 4. Responsive Design
 
@@ -55,113 +61,73 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Text scaling**: Layouts that break when text size increases
 - **Missing breakpoints**: No mobile/tablet variants
 
-**Score 0–4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
+**Score 0-4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
 
 ### 5. Anti-Patterns (CRITICAL)
 
 Check against ALL the **DON'T** guidelines in the frontend-design skill. Look for AI slop tells (AI color palette, gradient text, glassmorphism, hero metrics, card grids, generic fonts) and general design anti-patterns (gray on color, nested cards, bounce easing, redundant copy).
 
-**Score 0–4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
+**Score 0-4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
 
-**CRITICAL**: This is an audit, not a fix. Document issues thoroughly with clear explanations of impact. Use other commands to fix issues after audit.
-
-## Generate Comprehensive Report
+## Generate Report
 
 ### Audit Health Score
 
-Present the dimension scores as a table:
-
 | # | Dimension | Score | Key Finding |
 |---|-----------|-------|-------------|
-| 1 | Accessibility | ? | [most critical a11y issue or "—"] |
+| 1 | Accessibility | ? | [most critical a11y issue or "--"] |
 | 2 | Performance | ? | |
 | 3 | Responsive Design | ? | |
 | 4 | Theming | ? | |
 | 5 | Anti-Patterns | ? | |
 | **Total** | | **??/20** | **[Rating band]** |
 
-**Rating bands**:
-| Score | Rating | Action |
-|-------|--------|--------|
-| 18–20 | Excellent | Minor polish only |
-| 14–17 | Good | Address weak dimensions |
-| 10–13 | Acceptable | Significant work needed |
-| 6–9 | Poor | Major quality overhaul |
-| 0–5 | Critical | Fundamental issues across the board |
+**Rating bands**: 18-20 Excellent (minor polish), 14-17 Good (address weak dimensions), 10-13 Acceptable (significant work needed), 6-9 Poor (major overhaul), 0-5 Critical (fundamental issues)
 
 ### Anti-Patterns Verdict
-**Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
+**Start here.** Pass/fail: Does this look AI-generated? List specific tells. Be brutally honest.
 
 ### Executive Summary
 - Audit Health Score: **??/20** ([rating band])
 - Total issues found (count by severity: P0/P1/P2/P3)
-- Most critical issues (top 3-5)
+- Top 3-5 critical issues
 - Recommended next steps
 
 ### Detailed Findings by Severity
 
-Tag every issue with **P0–P3 severity**:
-| Priority | Name | Description |
-|----------|------|-------------|
-| **P0** | Blocking | Prevents task completion — fix immediately |
-| **P1** | Major | Significant difficulty or WCAG AA violation — fix before release |
-| **P2** | Minor | Annoyance, workaround exists — fix in next pass |
-| **P3** | Polish | Nice-to-fix, no real user impact — fix if time permits |
+Tag every issue with **P0-P3 severity**:
+- **P0 Blocking**: Prevents task completion — fix immediately
+- **P1 Major**: Significant difficulty or WCAG AA violation — fix before release
+- **P2 Minor**: Annoyance, workaround exists — fix in next pass
+- **P3 Polish**: Nice-to-fix, no real user impact — fix if time permits
 
 For each issue, document:
 - **[P?] Issue name**
-- **Location**: Where it occurs (component, file, line)
+- **Location**: Component, file, line
 - **Category**: Accessibility / Performance / Theming / Responsive / Anti-Pattern
-- **Description**: What the issue is
 - **Impact**: How it affects users
 - **WCAG/Standard**: Which standard it violates (if applicable)
 - **Recommendation**: How to fix it
-- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive — or other installed skills you're sure exist)
-
-#### P0 — Blocking Issues
-[Issues that prevent task completion or violate WCAG A]
-
-#### P1 — Major Issues
-[Significant usability/accessibility impact, WCAG AA violations]
-
-#### P2 — Minor Issues
-[Quality issues, WCAG AAA violations, performance concerns]
-
-#### P3 — Polish Issues
-[Minor inconsistencies, optimization opportunities]
+- **Suggested command**: Which command to use (prefer: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Patterns & Systemic Issues
 
-Identify recurring problems:
+Identify recurring problems that indicate systemic gaps rather than one-off mistakes:
 - "Hard-coded colors appear in 15+ components, should use design tokens"
 - "Touch targets consistently too small (<44px) throughout mobile experience"
-- "Missing focus indicators on all custom interactive components"
 
 ### Positive Findings
 
-Note what's working well:
-- Good practices to maintain
-- Exemplary implementations to replicate elsewhere
+Note what's working well — good practices to maintain and replicate.
 
 ## Recommended Actions
 
-Present a prioritized action summary. Order is determined by severity automatically (P0 first, then P1, then P2).
-
-### Action Summary
-
-List recommended commands in priority order:
+List recommended commands in priority order (P0 first, then P1, then P2):
 
 1. **[P?] `/command-name`** — Brief description (specific context from audit findings)
 2. **[P?] `/command-name`** — Brief description (specific context)
-...
 
-**Rules for recommendations**:
-- Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive
-- Order by severity: P0 issues first, then P1, then P2 (skip P3 unless user has few issues)
-- Each item's description should carry enough context that the command knows what to focus on
-- Map findings to the most appropriate command
-- Skip commands that would address zero issues
-- End with `/polish` as the final step if any fixes were recommended
+**Rules**: Only recommend commands from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive. Map findings to the most appropriate command. End with `/polish` as the final step if any fixes were recommended.
 
 After presenting the summary, tell the user:
 
@@ -173,10 +139,9 @@ After presenting the summary, tell the user:
 
 **NEVER**:
 - Report issues without explaining impact (why does this matter?)
-- Mix severity levels inconsistently
-- Skip positive findings (celebrate what works)
 - Provide generic recommendations (be specific and actionable)
+- Skip positive findings (celebrate what works)
 - Forget to prioritize (everything can't be P0)
 - Report false positives without verification
 
-Remember: You're a quality auditor with exceptional attention to detail. Document systematically, prioritize ruthlessly, and provide clear paths to improvement. A good audit makes fixing easy.
+Remember: You're a technical quality auditor. Document systematically, prioritize ruthlessly, cite specific code locations, and provide clear paths to improvement.

.trae/skills/critique/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: critique
-description: Evaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, cognitive load, and overall design quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design, UI, or component.
+description: Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
 user-invocable: true
 argument-hint: "[area (feature, page, component...)]"
 ---
@@ -11,7 +11,7 @@ Invoke /frontend-design — it contains design principles, anti-patterns, and th
 
 ---
 
-Conduct a holistic design critique, evaluating whether the interface actually works—not just technically, but as a designed experience. Think like a design director giving feedback.
+Conduct a holistic design critique, evaluating whether the interface actually works — not just technically, but as a designed experience. Think like a design director giving feedback.
 
 ## Phase 1: Design Critique
 
@@ -21,7 +21,7 @@ Evaluate the interface across these dimensions:
 
 **This is the most important check.** Does this look like every other AI-generated interface from 2024-2025?
 
-Review the design against ALL the **DON'T** guidelines in the frontend-design skill—they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
+Review the design against ALL the **DON'T** guidelines in the frontend-design skill — they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
 
 **The test**: If you showed this to someone and said "AI made this," would they believe you immediately? If yes, that's the problem.
 
@@ -31,20 +31,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Do size, color, and position communicate importance correctly?
 - Is there visual competition between elements that should have different weights?
 
-### 3. Information Architecture
-→ *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and checklist*
+### 3. Information Architecture & Cognitive Load
+> *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and 8-item checklist*
 - Is the structure intuitive? Would a new user understand the organization?
 - Is related content grouped logically?
 - Are there too many choices at once? Count visible options at each decision point — if >4, flag it
 - Is the navigation clear and predictable?
 - **Progressive disclosure**: Is complexity revealed only when needed, or dumped on the user upfront?
-- **Cognitive load sub-check**: Run the 8-item cognitive load checklist from the reference. Report the number of failures.
+- **Run the 8-item cognitive load checklist** from the reference. Report failure count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
 
 ### 4. Emotional Journey
-→ *Consult [cognitive-load](reference/cognitive-load.md) for emotional intervention patterns*
 - What emotion does this interface evoke? Is that intentional?
 - Does it match the brand personality?
-- Does it feel trustworthy, approachable, premium, playful—whatever it should feel?
+- Does it feel trustworthy, approachable, premium, playful — whatever it should feel?
 - Would the target user feel "this is for me"?
 - **Peak-end rule**: Is the most intense moment positive? Does the experience end well (confirmation, celebration, clear next step)?
 - **Emotional valleys**: Check for onboarding frustration, error cliffs, feature discovery gaps, or anxiety spikes at high-stakes moments (payment, delete, commit)
@@ -72,7 +71,7 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Is color used to communicate, not just decorate?
 - Does the palette feel cohesive?
 - Are accent colors drawing attention to the right things?
-- Does it work for colorblind users? (not just technically—does meaning still come through?)
+- Does it work for colorblind users? (not just technically — does meaning still come through?)
 
 ### 9. States & Edge Cases
 - Empty states: Do they guide users toward action, or just say "nothing here"?
@@ -86,27 +85,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Are labels and buttons unambiguous?
 - Does error copy help users fix the problem?
 
-### 11. Cognitive Load
-→ *Consult [cognitive-load](reference/cognitive-load.md)*
-- **Intrinsic vs. extraneous**: Is the mental effort coming from the task itself (acceptable) or from poor design choices (eliminate)?
-- **Decision points**: Count visible choices at key moments. More than 4 simultaneous options = overload.
-- **Working memory burden**: Does the user need to remember information from a previous screen to act on the current one?
-- **Information chunking**: Is content broken into digestible groups, or presented as undifferentiated walls?
-- Run the 8-item cognitive load checklist. Report failures count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
-
 ## Phase 2: Present Findings
 
 Structure your feedback as a design director would:
 
 ### Design Health Score
-→ *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
+> *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
 
 Score each of Nielsen's 10 heuristics 0–4. Present as a table:
 
 | # | Heuristic | Score | Key Issue |
 |---|-----------|-------|-----------|
 | 1 | Visibility of System Status | ? | [specific finding or "—" if solid] |
-| 2 | Match System ↔ Real World | ? | |
+| 2 | Match System / Real World | ? | |
 | 3 | User Control and Freedom | ? | |
 | 4 | Consistency and Standards | ? | |
 | 5 | Error Prevention | ? | |
@@ -123,13 +114,13 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score
 **Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
 
 ### Overall Impression
-A brief gut reaction—what works, what doesn't, and the single biggest opportunity.
+A brief gut reaction — what works, what doesn't, and the single biggest opportunity.
 
 ### What's Working
-Highlight 2-3 things done well. Be specific about why they work.
+Highlight 2–3 things done well. Be specific about why they work.
 
 ### Priority Issues
-The 3-5 most impactful design problems, ordered by importance.
+The 3–5 most impactful design problems, ordered by importance.
 
 For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](reference/heuristics-scoring.md) for severity definitions):
 - **[P?] What**: Name the problem clearly
@@ -138,7 +129,7 @@ For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](refe
 - **Suggested command**: Which command could address this (from: /animate, /quieter, /optimize, /adapt, /clarify, /distill, /delight, /onboard, /normalize, /audit, /harden, /polish, /extract, /bolder, /arrange, /typeset, /critique, /colorize, /overdrive)
 
 ### Persona Red Flags
-→ *Consult [personas](reference/personas.md)*
+> *Consult [personas](reference/personas.md)*
 
 Auto-select 2–3 personas most relevant to this interface type (use the selection table in the reference). If `RULES.md` contains a `## Design Context` section from `teach-impeccable`, also generate 1–2 project-specific personas from the audience/brand info.
 
@@ -154,12 +145,12 @@ Be specific — name the exact elements and interactions that fail each persona.
 Quick notes on smaller issues worth addressing.
 
 **Remember**:
-- Be direct—vague feedback wastes everyone's time
-- Be specific—"the submit button" not "some elements"
+- Be direct — vague feedback wastes everyone's time
+- Be specific — "the submit button" not "some elements"
 - Say what's wrong AND why it matters to users
 - Give concrete suggestions, not just "consider exploring..."
-- Prioritize ruthlessly—if everything is important, nothing is
-- Don't soften criticism—developers need honest feedback to ship great design
+- Prioritize ruthlessly — if everything is important, nothing is
+- Don't soften criticism — developers need honest feedback to ship great design
 
 ## Phase 3: Ask the User
 
@@ -167,9 +158,9 @@ Quick notes on smaller issues worth addressing.
 
 Ask questions along these lines (adapt to the specific findings — do NOT ask generic questions):
 
-1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2-3 issue categories as options.
+1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2–3 issue categories as options.
 
-2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2-3 tonal directions as options based on what would fix the issues found.
+2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2–3 tonal directions as options based on what would fix the issues found.
 
 3. **Scope**: Ask how much the user wants to take on. For example: "I found N issues. Want to address everything, or focus on the top 3?" Offer scope options like "Top 3 only", "All issues", "Critical issues only".
 
@@ -177,9 +168,9 @@ Ask questions along these lines (adapt to the specific findings — do NOT ask g
 
 **Rules for questions**:
 - Every question must reference specific findings from Phase 2 — never ask generic "who is your audience?" questions
-- Keep it to 2-4 questions maximum — respect the user's time
+- Keep it to 2–4 questions maximum — respect the user's time
 - Offer concrete options, not open-ended prompts
-- If findings are straightforward (e.g., only 1-2 clear issues), skip questions and go directly to Phase 4
+- If findings are straightforward (e.g., only 1–2 clear issues), skip questions and go directly to Phase 4
 
 ## Phase 4: Recommended Actions
 

.trae/skills/critique/reference/personas.md

@@ -88,30 +88,30 @@ Test the interface through the eyes of 5 distinct user archetypes. Each persona
 
 ---
 
-## 4. Skeptical Evaluator — "Riley"
+## 4. Deliberate Stress Tester — "Riley"
 
-**Profile**: Evaluating the product for their team or company. Looking for reasons to reject. Comparing against competitors.
+**Profile**: Methodical user who pushes interfaces beyond the happy path. Tests edge cases, tries unexpected inputs, and probes for gaps in the experience.
 
 **Behaviors**:
 - Tests edge cases intentionally (empty states, long strings, special characters)
-- Looks for pricing catches and hidden limitations
-- Reads fine print and terms of service
-- Tries to break things deliberately
+- Submits forms with unexpected data (emoji, RTL text, very long values)
+- Tries to break workflows by navigating backwards, refreshing mid-flow, or opening in multiple tabs
+- Looks for inconsistencies between what the UI promises and what actually happens
 - Documents problems methodically
 
 **Test Questions**:
 - What happens at the edges (0 items, 1000 items, very long text)?
-- Is pricing and value proposition transparent?
-- Are there hidden limitations or gotchas?
-- How polished is error handling?
-- What data is collected and why?
+- Do error states recover gracefully or leave the UI in a broken state?
+- What happens on refresh mid-workflow? Is state preserved?
+- Are there features that appear to work but produce broken results?
+- How does the UI handle unexpected input (emoji, special chars, paste from Excel)?
 
 **Red Flags** (report these specifically):
-- Hidden pricing or "contact sales" for basic information
-- Features that appear to work but produce broken results
-- Poor error handling that exposes technical details
-- Unclear data practices or missing privacy information
+- Features that appear to work but silently fail or produce wrong results
+- Error handling that exposes technical details or leaves UI in a broken state
 - Empty states that show nothing useful ("No results" with no guidance)
+- Workflows that lose user data on refresh or navigation
+- Inconsistent behavior between similar interactions in different parts of the UI
 
 ---
 
@@ -150,7 +150,7 @@ Choose personas based on the interface type:
 |---------------|-----------------|-----|
 | Landing page / marketing | Jordan, Riley, Casey | First impressions, trust, mobile |
 | Dashboard / admin | Alex, Sam | Power users, accessibility |
-| E-commerce / checkout | Casey, Riley, Jordan | Mobile, trust, clarity |
+| E-commerce / checkout | Casey, Riley, Jordan | Mobile, edge cases, clarity |
 | Onboarding flow | Jordan, Casey | Confusion, interruption |
 | Data-heavy / analytics | Alex, Sam | Efficiency, keyboard nav |
 | Form-heavy / wizard | Jordan, Sam, Casey | Clarity, accessibility, mobile |

source/skills/audit/SKILL.md

@@ -1,17 +1,23 @@
 ---
 name: audit
-description: "Perform a comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates a scored report with severity ratings and actionable plan. Use when the user wants a design review, accessibility check, quality audit, or a full list of UI issues to fix."
+description: "Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review."
 argument-hint: "[area (feature, page, component...)]"
 user-invocable: true
 ---
 
-Run systematic quality checks and generate a comprehensive audit report with quantitative scoring, prioritized issues, and an actionable plan. Don't fix issues — document them for other commands to address.
+## MANDATORY PREPARATION
 
-**First**: Invoke {{command_prefix}}frontend-design for design principles and anti-patterns.
+Invoke {{command_prefix}}frontend-design — it contains design principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no design context exists yet, you MUST run {{command_prefix}}teach-impeccable first.
+
+---
+
+Run systematic **technical** quality checks and generate a comprehensive report. Don't fix issues — document them for other commands to address.
+
+This is a code-level audit, not a design critique. Check what's measurable and verifiable in the implementation.
 
 ## Diagnostic Scan
 
-Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using the criteria below.
+Run comprehensive checks across 5 dimensions. Score each dimension 0-4 using the criteria below.
 
 ### 1. Accessibility (A11y)
 
@@ -23,7 +29,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Alt text**: Missing or poor image descriptions
 - **Form issues**: Inputs without labels, poor error messaging, missing required indicators
 
-**Score 0–4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
+**Score 0-4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
 
 ### 2. Performance
 
@@ -34,7 +40,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Bundle size**: Unnecessary imports, unused dependencies
 - **Render performance**: Unnecessary re-renders, missing memoization
 
-**Score 0–4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
+**Score 0-4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
 
 ### 3. Theming
 
@@ -44,7 +50,7 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Inconsistent tokens**: Using wrong tokens, mixing token types
 - **Theme switching issues**: Values that don't update on theme change
 
-**Score 0–4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
+**Score 0-4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
 
 ### 4. Responsive Design
 
@@ -55,113 +61,73 @@ Run comprehensive checks across 5 dimensions. Score each dimension 0–4 using t
 - **Text scaling**: Layouts that break when text size increases
 - **Missing breakpoints**: No mobile/tablet variants
 
-**Score 0–4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
+**Score 0-4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
 
 ### 5. Anti-Patterns (CRITICAL)
 
 Check against ALL the **DON'T** guidelines in the frontend-design skill. Look for AI slop tells (AI color palette, gradient text, glassmorphism, hero metrics, card grids, generic fonts) and general design anti-patterns (gray on color, nested cards, bounce easing, redundant copy).
 
-**Score 0–4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
+**Score 0-4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
 
-**CRITICAL**: This is an audit, not a fix. Document issues thoroughly with clear explanations of impact. Use other commands to fix issues after audit.
-
-## Generate Comprehensive Report
+## Generate Report
 
 ### Audit Health Score
 
-Present the dimension scores as a table:
-
 | # | Dimension | Score | Key Finding |
 |---|-----------|-------|-------------|
-| 1 | Accessibility | ? | [most critical a11y issue or "—"] |
+| 1 | Accessibility | ? | [most critical a11y issue or "--"] |
 | 2 | Performance | ? | |
 | 3 | Responsive Design | ? | |
 | 4 | Theming | ? | |
 | 5 | Anti-Patterns | ? | |
 | **Total** | | **??/20** | **[Rating band]** |
 
-**Rating bands**:
-| Score | Rating | Action |
-|-------|--------|--------|
-| 18–20 | Excellent | Minor polish only |
-| 14–17 | Good | Address weak dimensions |
-| 10–13 | Acceptable | Significant work needed |
-| 6–9 | Poor | Major quality overhaul |
-| 0–5 | Critical | Fundamental issues across the board |
+**Rating bands**: 18-20 Excellent (minor polish), 14-17 Good (address weak dimensions), 10-13 Acceptable (significant work needed), 6-9 Poor (major overhaul), 0-5 Critical (fundamental issues)
 
 ### Anti-Patterns Verdict
-**Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
+**Start here.** Pass/fail: Does this look AI-generated? List specific tells. Be brutally honest.
 
 ### Executive Summary
 - Audit Health Score: **??/20** ([rating band])
 - Total issues found (count by severity: P0/P1/P2/P3)
-- Most critical issues (top 3-5)
+- Top 3-5 critical issues
 - Recommended next steps
 
 ### Detailed Findings by Severity
 
-Tag every issue with **P0–P3 severity**:
-| Priority | Name | Description |
-|----------|------|-------------|
-| **P0** | Blocking | Prevents task completion — fix immediately |
-| **P1** | Major | Significant difficulty or WCAG AA violation — fix before release |
-| **P2** | Minor | Annoyance, workaround exists — fix in next pass |
-| **P3** | Polish | Nice-to-fix, no real user impact — fix if time permits |
+Tag every issue with **P0-P3 severity**:
+- **P0 Blocking**: Prevents task completion — fix immediately
+- **P1 Major**: Significant difficulty or WCAG AA violation — fix before release
+- **P2 Minor**: Annoyance, workaround exists — fix in next pass
+- **P3 Polish**: Nice-to-fix, no real user impact — fix if time permits
 
 For each issue, document:
 - **[P?] Issue name**
-- **Location**: Where it occurs (component, file, line)
+- **Location**: Component, file, line
 - **Category**: Accessibility / Performance / Theming / Responsive / Anti-Pattern
-- **Description**: What the issue is
 - **Impact**: How it affects users
 - **WCAG/Standard**: Which standard it violates (if applicable)
 - **Recommendation**: How to fix it
-- **Suggested command**: Which command to use (prefer: {{available_commands}} — or other installed skills you're sure exist)
-
-#### P0 — Blocking Issues
-[Issues that prevent task completion or violate WCAG A]
-
-#### P1 — Major Issues
-[Significant usability/accessibility impact, WCAG AA violations]
-
-#### P2 — Minor Issues
-[Quality issues, WCAG AAA violations, performance concerns]
-
-#### P3 — Polish Issues
-[Minor inconsistencies, optimization opportunities]
+- **Suggested command**: Which command to use (prefer: {{available_commands}})
 
 ### Patterns & Systemic Issues
 
-Identify recurring problems:
+Identify recurring problems that indicate systemic gaps rather than one-off mistakes:
 - "Hard-coded colors appear in 15+ components, should use design tokens"
 - "Touch targets consistently too small (<44px) throughout mobile experience"
-- "Missing focus indicators on all custom interactive components"
 
 ### Positive Findings
 
-Note what's working well:
-- Good practices to maintain
-- Exemplary implementations to replicate elsewhere
+Note what's working well — good practices to maintain and replicate.
 
 ## Recommended Actions
 
-Present a prioritized action summary. Order is determined by severity automatically (P0 first, then P1, then P2).
-
-### Action Summary
-
-List recommended commands in priority order:
+List recommended commands in priority order (P0 first, then P1, then P2):
 
 1. **[P?] `{{command_prefix}}command-name`** — Brief description (specific context from audit findings)
 2. **[P?] `{{command_prefix}}command-name`** — Brief description (specific context)
-...
 
-**Rules for recommendations**:
-- Only recommend commands from: {{available_commands}}
-- Order by severity: P0 issues first, then P1, then P2 (skip P3 unless user has few issues)
-- Each item's description should carry enough context that the command knows what to focus on
-- Map findings to the most appropriate command
-- Skip commands that would address zero issues
-- End with `{{command_prefix}}polish` as the final step if any fixes were recommended
+**Rules**: Only recommend commands from: {{available_commands}}. Map findings to the most appropriate command. End with `{{command_prefix}}polish` as the final step if any fixes were recommended.
 
 After presenting the summary, tell the user:
 
@@ -173,10 +139,9 @@ After presenting the summary, tell the user:
 
 **NEVER**:
 - Report issues without explaining impact (why does this matter?)
-- Mix severity levels inconsistently
-- Skip positive findings (celebrate what works)
 - Provide generic recommendations (be specific and actionable)
+- Skip positive findings (celebrate what works)
 - Forget to prioritize (everything can't be P0)
 - Report false positives without verification
 
-Remember: You're a quality auditor with exceptional attention to detail. Document systematically, prioritize ruthlessly, and provide clear paths to improvement. A good audit makes fixing easy.
+Remember: You're a technical quality auditor. Document systematically, prioritize ruthlessly, cite specific code locations, and provide clear paths to improvement.

source/skills/critique/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: critique
-description: "Evaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, cognitive load, and overall design quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design, UI, or component."
+description: "Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component."
 argument-hint: "[area (feature, page, component...)]"
 user-invocable: true
 ---
@@ -11,7 +11,7 @@ Invoke {{command_prefix}}frontend-design — it contains design principles, anti
 
 ---
 
-Conduct a holistic design critique, evaluating whether the interface actually works—not just technically, but as a designed experience. Think like a design director giving feedback.
+Conduct a holistic design critique, evaluating whether the interface actually works — not just technically, but as a designed experience. Think like a design director giving feedback.
 
 ## Phase 1: Design Critique
 
@@ -21,7 +21,7 @@ Evaluate the interface across these dimensions:
 
 **This is the most important check.** Does this look like every other AI-generated interface from 2024-2025?
 
-Review the design against ALL the **DON'T** guidelines in the frontend-design skill—they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
+Review the design against ALL the **DON'T** guidelines in the frontend-design skill — they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
 
 **The test**: If you showed this to someone and said "AI made this," would they believe you immediately? If yes, that's the problem.
 
@@ -31,20 +31,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Do size, color, and position communicate importance correctly?
 - Is there visual competition between elements that should have different weights?
 
-### 3. Information Architecture
-→ *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and checklist*
+### 3. Information Architecture & Cognitive Load
+> *Consult [cognitive-load](reference/cognitive-load.md) for the working memory rule and 8-item checklist*
 - Is the structure intuitive? Would a new user understand the organization?
 - Is related content grouped logically?
 - Are there too many choices at once? Count visible options at each decision point — if >4, flag it
 - Is the navigation clear and predictable?
 - **Progressive disclosure**: Is complexity revealed only when needed, or dumped on the user upfront?
-- **Cognitive load sub-check**: Run the 8-item cognitive load checklist from the reference. Report the number of failures.
+- **Run the 8-item cognitive load checklist** from the reference. Report failure count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
 
 ### 4. Emotional Journey
-→ *Consult [cognitive-load](reference/cognitive-load.md) for emotional intervention patterns*
 - What emotion does this interface evoke? Is that intentional?
 - Does it match the brand personality?
-- Does it feel trustworthy, approachable, premium, playful—whatever it should feel?
+- Does it feel trustworthy, approachable, premium, playful — whatever it should feel?
 - Would the target user feel "this is for me"?
 - **Peak-end rule**: Is the most intense moment positive? Does the experience end well (confirmation, celebration, clear next step)?
 - **Emotional valleys**: Check for onboarding frustration, error cliffs, feature discovery gaps, or anxiety spikes at high-stakes moments (payment, delete, commit)
@@ -72,7 +71,7 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Is color used to communicate, not just decorate?
 - Does the palette feel cohesive?
 - Are accent colors drawing attention to the right things?
-- Does it work for colorblind users? (not just technically—does meaning still come through?)
+- Does it work for colorblind users? (not just technically — does meaning still come through?)
 
 ### 9. States & Edge Cases
 - Empty states: Do they guide users toward action, or just say "nothing here"?
@@ -86,27 +85,19 @@ Review the design against ALL the **DON'T** guidelines in the frontend-design sk
 - Are labels and buttons unambiguous?
 - Does error copy help users fix the problem?
 
-### 11. Cognitive Load
-→ *Consult [cognitive-load](reference/cognitive-load.md)*
-- **Intrinsic vs. extraneous**: Is the mental effort coming from the task itself (acceptable) or from poor design choices (eliminate)?
-- **Decision points**: Count visible choices at key moments. More than 4 simultaneous options = overload.
-- **Working memory burden**: Does the user need to remember information from a previous screen to act on the current one?
-- **Information chunking**: Is content broken into digestible groups, or presented as undifferentiated walls?
-- Run the 8-item cognitive load checklist. Report failures count: 0–1 = low (good), 2–3 = moderate, 4+ = critical.
-
 ## Phase 2: Present Findings
 
 Structure your feedback as a design director would:
 
 ### Design Health Score
-→ *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
+> *Consult [heuristics-scoring](reference/heuristics-scoring.md)*
 
 Score each of Nielsen's 10 heuristics 0–4. Present as a table:
 
 | # | Heuristic | Score | Key Issue |
 |---|-----------|-------|-----------|
 | 1 | Visibility of System Status | ? | [specific finding or "—" if solid] |
-| 2 | Match System ↔ Real World | ? | |
+| 2 | Match System / Real World | ? | |
 | 3 | User Control and Freedom | ? | |
 | 4 | Consistency and Standards | ? | |
 | 5 | Error Prevention | ? | |
@@ -123,13 +114,13 @@ Be honest with scores. A 4 means genuinely excellent. Most real interfaces score
 **Start here.** Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
 
 ### Overall Impression
-A brief gut reaction—what works, what doesn't, and the single biggest opportunity.
+A brief gut reaction — what works, what doesn't, and the single biggest opportunity.
 
 ### What's Working
-Highlight 2-3 things done well. Be specific about why they work.
+Highlight 2–3 things done well. Be specific about why they work.
 
 ### Priority Issues
-The 3-5 most impactful design problems, ordered by importance.
+The 3–5 most impactful design problems, ordered by importance.
 
 For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](reference/heuristics-scoring.md) for severity definitions):
 - **[P?] What**: Name the problem clearly
@@ -138,7 +129,7 @@ For each issue, tag with **P0–P3 severity** (consult [heuristics-scoring](refe
 - **Suggested command**: Which command could address this (from: {{available_commands}})
 
 ### Persona Red Flags
-→ *Consult [personas](reference/personas.md)*
+> *Consult [personas](reference/personas.md)*
 
 Auto-select 2–3 personas most relevant to this interface type (use the selection table in the reference). If `{{config_file}}` contains a `## Design Context` section from `teach-impeccable`, also generate 1–2 project-specific personas from the audience/brand info.
 
@@ -154,12 +145,12 @@ Be specific — name the exact elements and interactions that fail each persona.
 Quick notes on smaller issues worth addressing.
 
 **Remember**:
-- Be direct—vague feedback wastes everyone's time
-- Be specific—"the submit button" not "some elements"
+- Be direct — vague feedback wastes everyone's time
+- Be specific — "the submit button" not "some elements"
 - Say what's wrong AND why it matters to users
 - Give concrete suggestions, not just "consider exploring..."
-- Prioritize ruthlessly—if everything is important, nothing is
-- Don't soften criticism—developers need honest feedback to ship great design
+- Prioritize ruthlessly — if everything is important, nothing is
+- Don't soften criticism — developers need honest feedback to ship great design
 
 ## Phase 3: Ask the User
 
@@ -167,9 +158,9 @@ Quick notes on smaller issues worth addressing.
 
 Ask questions along these lines (adapt to the specific findings — do NOT ask generic questions):
 
-1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2-3 issue categories as options.
+1. **Priority direction**: Based on the issues found, ask which category matters most to the user right now. For example: "I found problems with visual hierarchy, color usage, and information overload. Which area should we tackle first?" Offer the top 2–3 issue categories as options.
 
-2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2-3 tonal directions as options based on what would fix the issues found.
+2. **Design intent**: If the critique found a tonal mismatch, ask whether it was intentional. For example: "The interface feels clinical and corporate. Is that the intended tone, or should it feel warmer/bolder/more playful?" Offer 2–3 tonal directions as options based on what would fix the issues found.
 
 3. **Scope**: Ask how much the user wants to take on. For example: "I found N issues. Want to address everything, or focus on the top 3?" Offer scope options like "Top 3 only", "All issues", "Critical issues only".
 
@@ -177,9 +168,9 @@ Ask questions along these lines (adapt to the specific findings — do NOT ask g
 
 **Rules for questions**:
 - Every question must reference specific findings from Phase 2 — never ask generic "who is your audience?" questions
-- Keep it to 2-4 questions maximum — respect the user's time
+- Keep it to 2–4 questions maximum — respect the user's time
 - Offer concrete options, not open-ended prompts
-- If findings are straightforward (e.g., only 1-2 clear issues), skip questions and go directly to Phase 4
+- If findings are straightforward (e.g., only 1–2 clear issues), skip questions and go directly to Phase 4
 
 ## Phase 4: Recommended Actions
 

source/skills/critique/reference/personas.md

@@ -88,30 +88,30 @@ Test the interface through the eyes of 5 distinct user archetypes. Each persona
 
 ---
 
-## 4. Skeptical Evaluator — "Riley"
+## 4. Deliberate Stress Tester — "Riley"
 
-**Profile**: Evaluating the product for their team or company. Looking for reasons to reject. Comparing against competitors.
+**Profile**: Methodical user who pushes interfaces beyond the happy path. Tests edge cases, tries unexpected inputs, and probes for gaps in the experience.
 
 **Behaviors**:
 - Tests edge cases intentionally (empty states, long strings, special characters)
-- Looks for pricing catches and hidden limitations
-- Reads fine print and terms of service
-- Tries to break things deliberately
+- Submits forms with unexpected data (emoji, RTL text, very long values)
+- Tries to break workflows by navigating backwards, refreshing mid-flow, or opening in multiple tabs
+- Looks for inconsistencies between what the UI promises and what actually happens
 - Documents problems methodically
 
 **Test Questions**:
 - What happens at the edges (0 items, 1000 items, very long text)?
-- Is pricing and value proposition transparent?
-- Are there hidden limitations or gotchas?
-- How polished is error handling?
-- What data is collected and why?
+- Do error states recover gracefully or leave the UI in a broken state?
+- What happens on refresh mid-workflow? Is state preserved?
+- Are there features that appear to work but produce broken results?
+- How does the UI handle unexpected input (emoji, special chars, paste from Excel)?
 
 **Red Flags** (report these specifically):
-- Hidden pricing or "contact sales" for basic information
-- Features that appear to work but produce broken results
-- Poor error handling that exposes technical details
-- Unclear data practices or missing privacy information
+- Features that appear to work but silently fail or produce wrong results
+- Error handling that exposes technical details or leaves UI in a broken state
 - Empty states that show nothing useful ("No results" with no guidance)
+- Workflows that lose user data on refresh or navigation
+- Inconsistent behavior between similar interactions in different parts of the UI
 
 ---
 
@@ -150,7 +150,7 @@ Choose personas based on the interface type:
 |---------------|-----------------|-----|
 | Landing page / marketing | Jordan, Riley, Casey | First impressions, trust, mobile |
 | Dashboard / admin | Alex, Sam | Power users, accessibility |
-| E-commerce / checkout | Casey, Riley, Jordan | Mobile, trust, clarity |
+| E-commerce / checkout | Casey, Riley, Jordan | Mobile, edge cases, clarity |
 | Onboarding flow | Jordan, Casey | Confusion, interruption |
 | Data-heavy / analytics | Alex, Sam | Efficiency, keyboard nav |
 | Form-heavy / wizard | Jordan, Sam, Casey | Clarity, accessibility, mobile |