* skill: drop quality tiers, keep the real brand-craft guardrails Codex's craft/brand pass introduced fast/ship/showpiece "quality bars" plus brand-specific build gates, asset ledgers, sub-agent review, and self-graded fallback labels. In practice those tiers became escape hatches rather than craft pressure: the final output should always be 10/10, and the real decision points are splashiness and maximalism, not quality. Removed: - All quality-bar / showpiece / fast / ship framing in shape.md and craft.md - Standalone Brand Direction (#4) and Asset Requirements (#10) sections in shape's brief; renumbered back to 1-10 - The Brand hard rules section in brand.md (folded its real prohibitions into the existing Imagery and Brand bans sections) - Brand-specific build-gate item, mock-fidelity bullet, production-bar bullet, present-step bullet in craft.md - Asset ledger ceremony in craft Step 4 - Review-only sub-agents and "self-reviewed fallback, not independently validated" machinery in craft.md and polish.md - The For brand surfaces, assess hard failures subsection in polish.md and the brand checklist row - tests/brand-showpiece-reference.test.mjs (and its package.json wiring) Kept (the real nuggets): - Asset-substitution prohibition: image-led briefs ship real/generated assets or canvas/SVG/WebGL, not generic CSS panels, cards, bullets, or copy - Repeated tiny uppercase tracked kicker labels as a brand ban - Detector/QA output is defect evidence only, never proof of quality - "What visual assets are real content here?" discovery question - Inspect each major section individually for brand and long-form work - repeated-section-kickers detection rule + fixture - CLI improvements (JSON to stdout, -json/-fast aliases, severity field) - critique.md: npx impeccable detect --json fix Harness output dirs refreshed via bun run build. Full test suite (186) passes. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * skill: strip gate ceremony; require shape pause; allow compact briefs The setup gate table and IMPECCABLE_PREFLIGHT banner pushed every craft run through ritual restatement (PRODUCT.md → original prompt → round 1 → round 2 → 70-line "confirmed brief" → critique → summary, all saying the same thing). Replaced with imperative prose that still demands the same work but skips the user-facing telemetry. Specifically: SKILL.md - Drop the Setup gate table and IMPECCABLE_PREFLIGHT banner. - Keep the imperative steps explicitly: load context, identify register and load brand.md or product.md, AND load the matching command reference (craft.md / shape.md / etc.) when a sub-command is invoked. The command-reference step is non-negotiable; without craft.md loaded the agent skips the shape-and-confirm pause. craft.md - Drop the Build Gate / Craft Contract formal sections; replace with one paragraph stating prerequisites. - Step 1 explicitly requires ending the response after presenting the shape output; the user must confirm before any code lands. Allows a compact 3-5 bullet brief when the prompt + PRODUCT.md already pin direction (full 10-section structure reserved for genuinely ambiguous tasks). - Step 3 image gate skips silently when image generation isn't natively available; no user-facing announcement. - Step 6 explicitly legitimizes "first pass clean, shipping" as a valid endpoint and bans inventing fake defects to demonstrate iteration. shape.md - Cap discovery at 1 round by default; second round only when first leaves material gaps. - Adds an "assert-then-confirm, not menu-with-escape" rule: when PRODUCT.md and the prompt make one option obvious, name it and ask for confirm or override instead of enumerating "Restrained / Committed / Or something else?" as a real choice. - Phase 2 brief has two forms now: compact (default for clear briefs) and full structured (genuinely ambiguous). Open Questions can't double as leading-with-Recommend; if you'd write "Recommend: X", decide X. - Image gate same as craft.md. Validated end-to-end with a Haiku skill-on observability run: agent loads craft.md plus the brief's recommended implementation refs, pauses for one productive question (accent color, trace fidelity, CTA), and ships an artifact with zero side-tab violations vs. the original v1 baseline. Cost trades up modestly for that quality. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * craft.md Step 6: Reading the screenshot is the inspection, not taking it A v4 eval run took 4 targeted screenshots (hero, mobile, tablet, query-section) and then never Read any of them back. The agent treated browser_screenshot itself as "I inspected" and shipped without the multimodal feedback loop ever closing. Detector caught the resulting slop (5+ side-tab violations) on adjacent runs that did the same thing. Step 6 now spells out the pattern explicitly: take the screenshot, then Read the resulting PNG so its image content enters the conversation as multimodal input, then critique what you actually see in the image. With a check: "if your critique could have been written without looking at the image, you didn't look at the image." Validated with v5b: agent took 6 screenshots, Read all 6 back, and shipped with zero detector findings (vs the previous greenfield runs that hit 1-12 findings each). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * craft + brand: framework foundation, build-pipeline respect, image verification Three closely-linked additions surfaced by an eval-harness session investigating why the agent always shipped flat single-file HTML and zero imagery on greenfield brand briefs. 1. craft.md gains a new Step 0 "Project Foundation" before Shape. Detects existing framework / component library / icon set and uses what's there. Greenfield: ask the user via AskUserQuestion with sensible defaults framed by the brief (Astro for content/ brand sites, SvelteKit/Next/Nuxt for app surfaces, single index.html only for one-shot demos). Skipping the framework decision and writing flat HTML "to satisfy the spec" produces work that reads as a 2018 prototype regardless of visual quality. 2. craft.md Step 5 production bar gains two bullets: - Respect the build pipeline. Edit source files and run the project's `npm run build`; do not write to build/ / dist/ / .next/ directly with cat/heredoc/Bash redirects. Bypassing the pipeline skips asset hashing, image optimization, code splitting, and CSS extraction. - Verify external image URLs before referencing them. Use an image-search MCP, web-fetch tool, or browser if available; guessed photo IDs ship as broken-image placeholders. 3. brand.md "Imagery" section: - Generalizes the Unsplash URL guidance to "verify URLs before referencing them" with a hierarchy: image-search MCP > web-fetch > confidence-restricted manual selection > fewer photos. - Tightens the tech/dev-tool exception. Old line "zero imagery can be correct" gave models a permission slip. New framing keeps the underlying truth (typography + code + diagrams primarily carry voice) but raises the floor: imagery still earns its place when it serves the brief, and skipping it requires naming the typographic/diagrammatic move that's carrying the visual weight instead. "Zero imagery is the failure mode of laziness, not restraint." Eval-harness corpus that prompted this: 19/19 brand landing tasks shipped 0 images each, including ones where Opus had taste enough to break the dev-tool color default lane. The skill needs to teach both halves of the decision; the harness shouldn't have to nudge. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * detector: body-text-viewport-edge rule + OKLCH/var-resolution + anchor-inherit FP fixes New rule: body-text-viewport-edge flags body paragraphs that render flush against the left/right viewport edges (no container padding). Tested via the new tests/fixtures/antipatterns/body-text-viewport-edge.html fixture (3 flag cases, 5 pass cases) and the test in detect-antipatterns-browser. False-positive class fixes — all jsdom-mode only (real browsers resolve the cascade correctly so these gates stay inert there). Five related gaps that compounded into ~14× spurious contrast findings on Tailwind v4 pages with OKLCH color tokens: • OKLCH parser. jsdom returns the literal "oklch(...)" string from getComputedStyle; the detector now converts to sRGB via Björn Ottosson's matrices. Handles Tailwind v4's compact minified form "oklch(21.5%.02 50)" (no space after %). • var() resolution. resolveBackground + checkElementColors now accept the existing customPropMap and parse `var(--color-paper)` etc. as proper RGB via the new parseColorResolved helper. • bg-color before bg-image. The old order bailed on any gradient ancestor before checking for a solid background-color underneath, causing the body's decorative paper-grain gradient to be measured against instead of the page's actual `bg-paper` cream. • body/html-level gradient → white fallback. When the only opaque ancestor we can read is body/html with a gradient overlay (and jsdom can't decompose `background: var(--paper) gradient` to extract the solid color), return white instead of falling through to resolveGradientStops — which was picking up paper-grain noise colors and using them as the bg. • Anchor-inherit workaround for jsdom :link UA specificity. Tailwind v4's preflight declares `a { color: inherit }` (0,0,1). jsdom's UA stylesheet has `:link { color: blue }` at (0,1,1) and wins the cascade. Real Chrome wraps :link in :where() (0,0,0) so the page rule wins. When the page declares the inherit rule AND we see jsdom's default `rgb(0,0,238)` on an anchor, walk to the nearest non-anchor ancestor and use its color. • Alpha-fallback safety gate. When text has alpha<1 AND we couldn't find an opaque ancestor (effectiveBg null), skip the contrast finding. Covers any remaining FP class the deeper fixes miss. Verified end-to-end against an Opus iter-1 artifact on Tailwind v4 with 14 cream/cream FPs + 2 blue-link UA FPs before; 0 findings after, while the color.html fixture's 12 real low-contrast cases continue to flag (verified via direct detectHtml calls). cli/engine/detect-antipatterns-browser.js is the generated browser distribution — regenerated from .mjs via scripts/build-browser-detector.js (no manual edits to the generated file). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * craft.md: tighten verbose passages, de-codex Step 6, cut redundancies Cumulative reduction: 218 → 155 lines (-29%). Step 0: drop the "Why this matters" paragraph at the end. The body of Step 0 already makes the framework-pick point; the paragraph just re-explains it with extra rhetoric. Step 1: replace the 4-sentence "you must end your response" block with a single line. The original said the same thing three different ways. Step 3: trim the conditional / defensive scaffolding (Purpose subsection, "do not skip because the eventual UI is semantic..." paragraph, duplicated approval-loop guidance). Mock fidelity inventory preserved. Step 4: drop the "keep UI text semantic" sentence; it duplicates Step 5's "Semantic first" rule. The rasterized-vs-semantic decision rule stays. Step 5: tighten each production-bar bullet to bold-lead + specifics format. All 15 rules preserved (real content, mock ingredients, semantic first, spacing/alignment, typography, state coverage, interaction quality, icon set, build pipeline, image URL verification, optimized imagery, premium motion, maintainability, technical cleanliness, ask-when-uncertain). Step 6: rewrite around "look at what you built like a designer would — your eyes are whatever the harness gives you." Drops Codex-specific "In Codex, use browser-use" bias. Drops the verbose 3-step Read pattern (condensed to one sentence). Drops the 1-8 numbered checklist (replaced by a tight paragraph). Keeps the load-bearing rules: read the PNG, don't fabricate iteration, mock fidelity reference, exit bar = studio defensibility. Step 7: drop the closing "Iterate based on feedback. Good design is rarely right on the first pass" preachy filler. All em-dashes converted to semicolons / colons / periods to satisfy the skill prose validator. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * build: native subagent pipeline + Codex-only asset producer Adds an agent cross-compile pipeline alongside the existing skill pipeline. Sources live at skill/agents/*.md; providers that declare agentFormat (codex-toml, claude-md) emit native subagent files. An optional providers: <list> field on an agent gates which harnesses get a copy; default (no field) ships everywhere. The impeccable-asset-producer agent is opt-in to Codex only. It's useful for Codex's native image generation path and is untested elsewhere; Claude has no native image gen anyway. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * brand: inverse-test + cultural-symbol palette guardrail Two additions to the brand register reference: - Inverse slop test: describe the page the way a competitor would describe theirs. If that sentence fits the modal landing page in the category, restart. - Palette guardrail: when a cultural-symbol palette is the obvious pull, reach past it. Let cultural reading come from typography, imagery, and copy. Harness mirrors regenerated; some also catch up to the image- verification paragraph frome3ad2efthat hadn't been re-synced. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * PRODUCT.md: widen audience beyond developers Designers, product managers, and engineers all use AI coding tools and want better design output. Keeping the audience narrow to "frontend and full-stack developers" understates who the skill is actually for. Also retitles "developer" to "user/builder" in the purpose statement. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * site + build: bump rule count to 29, strip changelog from detector check Two changes: - site/pages/index.astro: three live mentions of "28 rules / checks" bumped to 29 after the body-text-viewport-edge rule landed inb9bf496. - scripts/build.js: the detection-count validator was reading the unstripped content, so historical counts inside changelog entries (e.g. "28 rules" from an older release note) were flagging against the current detector total. The command-count check already strips the changelog ul; the detection check now does the same. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * test: align hero-eyebrow-chip fixture with relaxed rule gatesb9bf496intentionally relaxed two gates in checkHeroEyebrow: - removed the heading-size ≥ 48px anchor (modern hero h1s use clamp/vw/var that jsdom can't resolve) - raised the eyebrow text ceiling from 30 to 60 chars Two fixture cases that satisfied the negative side of the old gates now match the rule: - "Body-Sized Heading Below Eyebrow" — 24px h1 with tracked-caps label above. Per the rule's stated intent ("a tiny tan label directly above any h1 is the antipattern regardless of how big the h1 ends up"), this is a flag. - "Long Uppercase Sentence Above Hero" — 46-char tracked-caps label is under the new 60-char ceiling, so still eyebrow-shaped. Both cases moved from the should-pass column to should-flag, with case descriptions rewritten to explain the gate they exercise. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Paul Bakaus <paulbakaus@pauls-mbp-3.lan> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
13 KiB
name, description, argument-hint, user-invocable, allowed-tools, license
| name | description | argument-hint | user-invocable | allowed-tools | license | |
|---|---|---|---|---|---|---|
| impeccable | Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks. | [{{command_hint}}] [target] | true |
|
Apache 2.0. Based on Anthropic's frontend-design skill. See NOTICE.md for attribution. |
Designs and iterates production-grade frontend interfaces. Real working code, committed design choices, exceptional craft.
Setup
Before any design work or file edits:
- Load context (PRODUCT.md / DESIGN.md) via the loader script.
- Identify the register and load the matching register reference (brand.md or product.md).
- If the user invoked a sub-command (e.g.
craft,shape,audit), load its reference file too. This is non-negotiable:craftwithoutcraft.mdloaded means you'll skip the shape-and-confirm step the user expects.
Skipping these produces generic output that ignores the project.
1. Context gathering
Two files, case-insensitive. The loader looks at the project root by default and falls back to .agents/context/ and docs/ if the root is clean. Override with IMPECCABLE_CONTEXT_DIR=path/to/dir (absolute or relative to cwd).
- PRODUCT.md: required. Users, brand, tone, anti-references, strategic principles.
- DESIGN.md: optional, strongly recommended. Colors, typography, elevation, components.
Load both in one call:
node {{scripts_path}}/load-context.mjs
Consume the full JSON output. Never pipe through head, tail, grep, or jq. The output's contextDir field tells you where the files were resolved from.
If the output is already in this session's conversation history, don't re-run. Exceptions requiring a fresh load: you just ran {{command_prefix}}impeccable teach or {{command_prefix}}impeccable document (they rewrite the files), or the user manually edited one.
{{command_prefix}}impeccable live already warms context via live.mjs. If you've run live.mjs, don't also run load-context.mjs this session.
If PRODUCT.md is missing, empty, or placeholder ([TODO] markers, <200 chars): run {{command_prefix}}impeccable teach, then resume the user's original task with the fresh context. If the original task was {{command_prefix}}impeccable craft, resume into {{command_prefix}}impeccable shape before any implementation work.
If DESIGN.md is missing: nudge once per session ("Run {{command_prefix}}impeccable document for more on-brand output"), then proceed.
2. Register
Every design task is brand (marketing, landing, campaign, long-form content, portfolio: design IS the product) or product (app UI, admin, dashboard, tool: design SERVES the product).
Identify before designing. Priority: (1) cue in the task itself ("landing page" vs "dashboard"); (2) the surface in focus (the page, file, or route being worked on); (3) register field in PRODUCT.md. First match wins.
If PRODUCT.md lacks the register field (legacy), infer it once from its "Users" and "Product Purpose" sections, then cache the inferred value for the session. Suggest the user run {{command_prefix}}impeccable teach to add the field explicitly.
Load the matching reference: reference/brand.md or reference/product.md. The shared design laws below apply to both.
Shared design laws
Apply to every design, both registers. Match implementation complexity to the aesthetic vision: maximalism needs elaborate code, minimalism needs precision. Interpret creatively. Vary across projects; never converge on the same choices. {{model}} is capable of extraordinary work. Don't hold back.
Color
- Use OKLCH. Reduce chroma as lightness approaches 0 or 100; high chroma at extremes looks garish.
- Never use
#000or#fff. Tint every neutral toward the brand hue (chroma 0.005–0.01 is enough). - Pick a color strategy before picking colors. Four steps on the commitment axis:
- Restrained: tinted neutrals + one accent ≤10%. Product default; brand minimalism.
- Committed: one saturated color carries 30–60% of the surface. Brand default for identity-driven pages.
- Full palette: 3–4 named roles, each used deliberately. Brand campaigns; product data viz.
- Drenched: the surface IS the color. Brand heroes, campaign pages.
- The "one accent ≤10%" rule is Restrained only. Committed / Full palette / Drenched exceed it on purpose. Don't collapse every design to Restrained by reflex.
Theme
Dark vs. light is never a default. Not dark "because tools look cool dark." Not light "to be safe."
Before choosing, write one sentence of physical scene: who uses this, where, under what ambient light, in what mood. If the sentence doesn't force the answer, it's not concrete enough. Add detail until it does.
"Observability dashboard" does not force an answer. "SRE glancing at incident severity on a 27-inch monitor at 2am in a dim room" does. Run the sentence, not the category.
Typography
- Cap body line length at 65–75ch.
- Hierarchy through scale + weight contrast (≥1.25 ratio between steps). Avoid flat scales.
Layout
- Vary spacing for rhythm. Same padding everywhere is monotony.
- Cards are the lazy answer. Use them only when they're truly the best affordance. Nested cards are always wrong.
- Don't wrap everything in a container. Most things don't need one.
Motion
- Don't animate CSS layout properties.
- Ease out with exponential curves (ease-out-quart / quint / expo). No bounce, no elastic.
Absolute bans
Match-and-refuse. If you're about to write any of these, rewrite the element with different structure.
- Side-stripe borders.
border-leftorborder-rightgreater than 1px as a colored accent on cards, list items, callouts, or alerts. Never intentional. Rewrite with full borders, background tints, leading numbers/icons, or nothing. - Gradient text.
background-clip: textcombined with a gradient background. Decorative, never meaningful. Use a single solid color. Emphasis via weight or size. - Glassmorphism as default. Blurs and glass cards used decoratively. Rare and purposeful, or nothing.
- The hero-metric template. Big number, small label, supporting stats, gradient accent. SaaS cliché.
- Identical card grids. Same-sized cards with icon + heading + text, repeated endlessly.
- Modal as first thought. Modals are usually laziness. Exhaust inline / progressive alternatives first.
Copy
- Every word earns its place. No restated headings, no intros that repeat the title.
- No em dashes. Use commas, colons, semicolons, periods, or parentheses. Also not
--.
The AI slop test
If someone could look at this interface and say "AI made that" without doubt, it's failed. Cross-register failures are the absolute bans above. Register-specific failures live in each reference.
Category-reflex check. Run at two altitudes; the second one catches what the first one misses.
- First-order: if someone could guess the theme + palette from the category alone ("observability → dark blue", "healthcare → white + teal", "finance → navy + gold", "crypto → neon on black"), it's the first training-data reflex. Rework the scene sentence and color strategy until the answer isn't obvious from the domain.
- Second-order: if someone could guess the aesthetic family from category-plus-anti-references ("AI workflow tool that's not SaaS-cream → editorial-typographic", "fintech that's not navy-and-gold → terminal-native dark mode"), it's the trap one tier deeper. The first reflex was avoided; the second wasn't. Rework until both answers are not obvious. The brand register's reflex-reject aesthetic lanes list catches the currently-saturated families.
Commands
| Command | Category | Description | Reference |
|---|---|---|---|
craft [feature] |
Build | Shape, then build a feature end-to-end | reference/craft.md |
shape [feature] |
Build | Plan UX/UI before writing code | reference/shape.md |
teach |
Build | Set up PRODUCT.md and DESIGN.md context | reference/teach.md |
document |
Build | Generate DESIGN.md from existing project code | reference/document.md |
extract [target] |
Build | Pull reusable tokens and components into design system | reference/extract.md |
critique [target] |
Evaluate | UX design review with heuristic scoring | reference/critique.md |
audit [target] |
Evaluate | Technical quality checks (a11y, perf, responsive) | reference/audit.md |
polish [target] |
Refine | Final quality pass before shipping | reference/polish.md |
bolder [target] |
Refine | Amplify safe or bland designs | reference/bolder.md |
quieter [target] |
Refine | Tone down aggressive or overstimulating designs | reference/quieter.md |
distill [target] |
Refine | Strip to essence, remove complexity | reference/distill.md |
harden [target] |
Refine | Production-ready: errors, i18n, edge cases | reference/harden.md |
onboard [target] |
Refine | Design first-run flows, empty states, activation | reference/onboard.md |
animate [target] |
Enhance | Add purposeful animations and motion | reference/animate.md |
colorize [target] |
Enhance | Add strategic color to monochromatic UIs | reference/colorize.md |
typeset [target] |
Enhance | Improve typography hierarchy and fonts | reference/typeset.md |
layout [target] |
Enhance | Fix spacing, rhythm, and visual hierarchy | reference/layout.md |
delight [target] |
Enhance | Add personality and memorable touches | reference/delight.md |
overdrive [target] |
Enhance | Push past conventional limits | reference/overdrive.md |
clarify [target] |
Fix | Improve UX copy, labels, and error messages | reference/clarify.md |
adapt [target] |
Fix | Adapt for different devices and screen sizes | reference/adapt.md |
optimize [target] |
Fix | Diagnose and fix UI performance | reference/optimize.md |
live |
Iterate | Visual variant mode: pick elements in the browser, generate alternatives | reference/live.md |
Plus two management commands: pin <command> and unpin <command>, detailed below.
Routing rules
- No argument: render the table above as the user-facing command menu, grouped by category. Ask what they'd like to do.
- First word matches a command: load its reference file and follow its instructions. Everything after the command name is the target.
- First word doesn't match: general design invocation. Apply the setup steps, shared design laws, and the loaded register reference, using the full argument as context.
Setup (context gathering, register) is already loaded by then; sub-commands don't re-invoke {{command_prefix}}impeccable.
If the first word is craft, setup still runs first, but reference/craft.md owns the rest of the flow. If setup invokes teach as a blocker, finish teach, refresh context, then resume the original command and target.
Pin / Unpin
Pin creates a standalone shortcut so {{command_prefix}}<command> invokes {{command_prefix}}impeccable <command> directly. Unpin removes it. The script writes to every harness directory present in the project.
node {{scripts_path}}/pin.mjs <pin|unpin> <command>
Valid <command> is any command from the table above. Report the script's result concisely. Confirm the new shortcut on success, relay stderr verbatim on error.