Commands now require context gathering before proceeding:
- bolder: target audience, use-cases, brand personality
- quieter: purpose, audience, what's working
- colorize: brand colors, audience, domain appropriateness
- animate: personality, performance budget, audience
- delight: brand personality, emotional context, appropriateness
- simplify: what's essential vs nice-to-have
Each command now:
1. Gathers context from thread/codebase first
2. MUST ask user if inference confidence is medium or lower
3. MUST use frontend-design skill before proceeding
4. Has visual separator (---) as hard gate before design work
This prevents AI slop by ensuring commands have proper context
before making design decisions.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add "MANDATORY: Context Gathering (Do This First)" section with 3 procedural steps
- Require scanning codebase for README, brand guidelines, design tokens before design
- Must answer: target audience, brand personality, existing tokens/colors/fonts
- Hard gate: STOP and ask user if ANY question is unclear
- Visual separator (---) prevents proceeding without completing steps
- Preserves full Tone options and Design Direction content
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Monospace is fine when used intentionally - the issue is lazy "dev tool"
defaults, not the typeface itself.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added explicit AI SLOP TRAP warning before planning
- Removed "monospace as accent" suggestion (contradicts skill)
- Replaced glassmorphism with grain, halftone, duotone alternatives
- Added anti-slop caveats to shadows and borders suggestions
- Added "NOT AI slop" as first verification check
- Added "the test" to verify section
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Restored DO/DON'T format in individual sections (required for website)
- Added new "Visual Details" section for glassmorphism, sparklines, etc.
- Added new AI slop patterns: gradient text, dark mode with glowing accents,
hero metric layout, identical card grids, thick colored border on one side
- Added "The AI Slop Test" section for commands to reference
- Commands now reference "DON'T guidelines" (one source of truth)
- Build now shows 16 pattern categories (was 0)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Removed scattered DON'Ts from individual Frontend Aesthetics sections
- Created ONE "Anti-Patterns (CRITICAL)" section with two sub-sections:
- AI Slop Tells: cyan-on-dark, gradient text, glassmorphism, hero metrics, etc.
- Design Anti-Patterns: gray on color, nested cards, bounce easing, etc.
- Added new pattern: "Rounded element with thick colored border on one side"
- Commands now reference the skill's Anti-Patterns section instead of duplicating
- Easier to maintain: one place to update
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Critical addition: Both commands now check for AI-generated aesthetic tells:
- Cyan-on-dark, purple-to-blue gradients, neon accents
- Gradient text, glassmorphism, hero metric layouts
- Monospace typography, sparklines as decoration
- Identical card grids, generic fonts, rounded rectangles
Reports now start with "AI Slop Verdict" - pass/fail on distinctiveness.
This is the most important quality signal for shipping work that doesn't
look like every other AI-generated interface.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Commands now say "Use the frontend-design skill" instead of passive note
- Skill's Design Thinking section now has explicit MUST-know checklist
- Added ask instruction to bolder command for context gathering
- AskUserQuestionTool instruction is now more prominent and imperative
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replaced placeholder divs with actual before/after webp images
for all three transformation examples.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Changed from passive "use the AskUserQuestion tool" to imperative
"STOP and call the AskUserQuestion tool" to ensure Claude actually
asks clarifying questions when context is missing.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Covers:
- Where to put downloaded files (project vs global)
- Troubleshooting missing commands/skills
- Getting started resources for beginners
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove margin-top: auto which caused whitespace on cards without
setup instructions. Buttons now flow naturally with consistent spacing.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Cursor Agent Skills also require setup:
1. Switch to Nightly channel
2. Enable Agent Skills in Settings → Rules
Added collapsible instructions to Cursor download card and README.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Gemini CLI now supports Agent Skills (experimental), so we can use the
standard .gemini/skills/ directory format instead of context file workarounds.
Changes:
- Update Gemini transformer to output proper skills directory structure
- Add collapsible setup instructions to Gemini download card
- Update README with Gemini CLI skills setup instructions
- Fix /review -> /critique in README command table
- Remove old GEMINI.md context file workaround
Setup requires:
1. npm i -g @google/gemini-cli@preview
2. /settings -> enable Skills
3. /skills list to verify
Docs: https://geminicli.com/docs/cli/skills/
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This endpoint was in the local server but missing from Vercel serverless
functions, causing "Source not available" on the deployed site.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Gemini does get skill content via GEMINI.frontend-design.md imports,
just not through a native skill system. Updated note to reflect this.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Users can now toggle "Prefix commands with /i-" in the download section
to get bundles with all commands prefixed (e.g., /i-audit instead of /audit).
This helps avoid conflicts with existing custom commands.
Build system changes:
- Transformers now accept optional prefix/outputSuffix parameters
- Build generates both unprefixed and i-prefixed variants
- ZIP bundles created for both variants
UI changes:
- Add toggle switch to download section
- Toggle controls which bundle variant gets downloaded
- Styled to match existing design language
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The /review command conflicts with a built-in Claude Code command.
Renamed to /critique which better reflects design terminology.
- Rename source/commands/review.md → critique.md
- Update command content and descriptions
- Rename demo file and update references
- Update data.js command mappings
- Update case study example in index.html
- Rebuild dist files for all providers
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add X/Twitter and LinkedIn social icons to footer
- Add "Renaissance Geek" newsletter button with arrow animation
- Create dedicated author section with subtle divider styling
- Responsive layout that stacks on mobile
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Convert "See It In Action" section to tabbed interface for space efficiency
- Add CLAUDE.md with project instructions for CSS build process
- Update README with additional documentation
- Enhance glass terminal component
- Add new API handlers and server routes
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Rewrite README to be user-focused (move dev info to DEVELOP.md)
- Credit Anthropic's original frontend-design skill
- Change license from MIT to Apache 2.0 for consistency
- Add NOTICE.md with proper attribution
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add meta description and OpenGraph tags for social sharing
- Create OG image (SVG)
- Fix README: "Design Language" → "Impeccable"
- Fix DEVELOP.md: update build script line count
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- New carousel + demo + info layout for commands on mobile (<900px)
- Add touch support to framework viz (tap instead of hover)
- Fix split-content width for demo comparisons
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Hero: simpler, factual description
- Problem section: remove em dash, less dramatic
- Antidote: properly credit Anthropic's original skill
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Clarify: 1 skill with 7 reference files (not 8 separate skills)
- Add "The Problem" section about AI design bias
- Simplify installation and usage sections
- Add patterns/anti-patterns summary
- Add author credit
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- 80ms threshold for "instant" perception
- Active vs passive time (preemptive start, early completion)
- Optimistic UI patterns with appropriate use cases
- Easing affects perceived duration (peak-end effect)
- Caution: too-fast can decrease perceived value
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Reduced to most impactful items only:
- Typography: modular scale, distinctive fonts, avoid overused fonts
- Color: off-whites/near-blacks, modern CSS, no gray on color, always tint
- Layout: visual rhythm, asymmetry, grid-breaking, no card obsession, modals are lazy
- Motion: no layout animation, no bounce/elastic
- Interaction: no redundant copy
- Responsive: don't hide mobile functionality
9 categories, ~15 items total - lean and focused.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Removed items that are:
- Accessibility 101 (WCAG, color blindness, reduced motion, focus indicators)
- Basic design principles (hierarchy, readability, semantic tokens)
- Well-known rules (2-3 fonts max, mobile-first, decorative body fonts)
Kept items that fight specific AI biases:
- Off-whites/near-blacks, dominant color with accents
- Spacing scales, asymmetry, staggered reveals
- Bounce/elastic easing ban, cards-on-cards
- Gray text on color, placeholder-as-labels, generic errors
Reduced from 60 items to 34 - more focused and actionable.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Updated claude-code transformer to generate markdown from YAML patterns/antipatterns
- Removed redundant prose body from patterns.md
- SKILL.md now contains detailed lists (5 items per category) instead of condensed prose
- patterns.md YAML frontmatter is now the single source of truth for both:
- Website API (/api/patterns)
- Generated skill files
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Before/after split comparison now appears immediately after the lead text
- Replaced verbose 6-card bias grid with compact horizontal tag row
- Demo is now the hero moment, biases are supporting context
- Better visual hierarchy and flow
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
