Design Audit
Check designs for accessibility, motion, colors, responsiveness, and performance issues.
Installation
- Make sure Claude is on your device and in your terminal.
Skills load from
~/.claude/skills/when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into Claude Code or into your terminal.
This copies the whole skill folder into
~/.claude/skills/design-audit-athevon/— the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Works for every skill.What this command does
- Makes a new, empty temporary folder.
- Downloads the skill's folder,
skills/_jutsu/design-audit, fromgithub.com/AThevon/genjutsu(branchmain), the GitHub repository it's listed from. You get the version that is there now, not a copy we keep. - Copies that folder to
~/.claude/skills/design-audit-athevon/. - Deletes the temporary folder.
Installing runs none of the skill's files; it only downloads and copies them. When you later use the skill, Claude follows its SKILL.md and may run scripts that come with it. Read them first.
Faster alternative (instruction-only skills)
Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.
Quick install (SKILL.md only)Sign up to copy - Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from
~/.claude/skills/). New skills are picked up on startup. - Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.
Prefer to read the source first? Open on GitHub.
When Claude uses it
Design audit checklist - motion gaps, accessibility, color consistency, responsive, performance.
What this skill does
Version-sensitive. Every API name, SDK gate and browser-support claim below was verified on 2026-09-08 against primary sources. What against, and when, is in
_jutsu/VERSIONS.md. If that date is old, re-verify before acting on a version number.
Design Audit
The final checkpoint. Loaded by
/genjutsu:paintat the end of the pipeline. Scans the codebase for motion gaps, a11y violations, perf issues, and inconsistencies.
The static pass
Run the script. Do not hand-write the greps.
python3 "$SKILL_BASE/design-audit/scripts/audit.py" .
Add --json if you want to post-process it. --only <check-id> runs one check, --group tells or
--group hygiene runs one group.
It reports three things, and the distinction between the last two is the whole reason it exists:
- findings - the check ran and found something. Every finding carries
file:lineand the matched text, so you report the evidence rather than a verdict. - clean - the check ran against real files and found nothing.
- not applicable - there were no files of that type, so the check did not run. Report these as not checked. Never as passing.
These greps used to live in this file, anchored on src/. A default Next.js app-router or
Nuxt 3 project has no src/, so they matched nothing, and the pipeline read the empty output as
a clean bill of health and said so to the user right before delivery. The script detects its
roots, skips node_modules and build output, covers .vue / .svelte / .astro alongside JSX
and CSS, and has a test per check asserting that the check can still fire.
Tells are reported apart. The script also runs the tells group: eighteen checks for
defaults a model reaches for when nothing asked for them, such as a numbered eyebrow, a weather
strip, three equal cards or a U+2014 (em dash) in the copy. Most read the displayed text of the
markup (text between tags, alt, title, aria-label, placeholder), never class names or
style objects, so width: "100%" is never taken for a claim of perfection. Five read the source
instead, because their tell is a class or a CSS rule: gradient text, glass, glow, blobs and
perpetual motion. Copy held in
JavaScript data (an array of features, a content file) is not displayed text to the script: read
it by hand.
They land in their own section, "Tells - confront each with the thesis before counting it",
always at nice-to-have, and the script never counts one as a problem, because it cannot read
the thesis. You confront each one:
- the validated thesis names the pattern (it says the studio works across Paris and Tokyo, and the header shows both clocks): list it as allowed by the thesis, with the sentence quoted;
- it does not: the tell is a problem, and it counts with the other problems.
A mood word names nothing. "Editorial" or "agency" does not allow a numbered eyebrow; most tells
are exactly the clichés those words summon. When the tells module was loaded, its rules decide.
The inventory also lists colours, radii and font families next to durations and easings, each
value with up to five file:line locations. No verdict there: compare them with the tokens and
the thesis.
Contrast is not in the script. Compute it yourself from the token values you emitted, and
report the pair with the ratio: #831843 on #FDF2F8 = 9.4:1. 4.5:1 for body text, 3:1 for large
text and UI boundaries. A swatch you looked at is not a measurement.
If python3 is unavailable, say so in one line and fall back to reading the components you
touched, in this order: reduced-motion guard, exit animations, layout-property animations, focus
visibility, click handlers on non-interactive elements. Report it as a partial audit, and say
which checks you could not run.
Stack-specific audit
Pick the subsection matching the project stack.
Compose (Android / Multiplatform)
- Run Layout Inspector (Android Studio): inspect recompositions, identify components recomposing on every state change.
- Run Macrobenchmark (
androidx.benchmark.macro): measure frame timing on a real device under representative scrolling / animation load. Target: <16.67ms per frame at 60fps, <8.33ms at 120fps. - Inspect recomposition counts: Layout Inspector > Component Tree > View Options > Show Recomposition Counts (API 29+, Compose 1.2+). Reset the counters before each interaction so the numbers mean something. There is no
Modifier.recomposeHighlighterin androidx - it is a sample you vendor into a debug source set. - Generate Baseline Profiles (
BaselineProfileGenerator) for production builds. - Verify
Modifier.semanticsis set on custom components (TalkBack support).
SwiftUI (iOS / macOS)
- Run Instruments Time Profiler: identify hot paths during animation (target: zero frames over 16.67ms).
- Run Instruments Hitches Instrument (iOS 14+): detects dropped frames and stalls.
- Run Instruments GPU Frame Capture for Metal shaders: verify shader compile time, GPU vs CPU bottleneck.
- Verify
.accessibilityLabel/.accessibilityHinton every interactive view. - Test with Dynamic Type at 200% size (
Environment Overridesin Xcode). - Test with Reduce Motion ON.
Web
- Existing checklist above (Lighthouse, Chrome DevTools Performance, etc.).
Output Format
Structure findings by severity:
Critical (must fix before ship)
- Missing
prefers-reduced-motionhandling - Clickable divs without keyboard support
outline: nonewithout:focus-visiblereplacement- Animating layout properties (width/height/top/left)
Important (fix in current sprint)
- Conditional renders without
AnimatePresence - Hover states without transition
- Missing
aria-hiddenon decorative animations setTimeoutused for animation loops- Inconsistent durations (>8 unique values)
Nice-to-have (backlog)
- Lists without stagger animation
- Inline styles without transition
- Excessive
will-changeusage - Asymmetric enter/exit (wrong direction)
- Animation library oversized for actual usage
Related skills
Generative Code Art
anthropics
Create algorithmic art with p5.js using randomness and interactive parameters.
UI/UX Pro Max
anthropics
Build production-grade web components and interfaces with distinctive, polished design.
Artifact Theme Toolkit
anthropics
Apply professional color and font themes to slides, docs, and web pages.
Multi-Component Web Artifacts
anthropics
Build complex React artifacts with Tailwind CSS and shadcn/ui components.