- name
SKILL.md
Die Skill-Datei bleibt im Repository des Herausgebers.
Fügen Sie den kopierten Befehl in ein Terminal ein. Er installiert diese SKILL.md in dem jeweiligen Agenten.
npx skills add AThevon/genjutsu --skill design-audit -a cursor -yFügen Sie den kopierten Befehl in ein Terminal ein. Er installiert diese SKILL.md in dem jeweiligen Agenten.
npx skills add AThevon/genjutsu --skill design-audit -a claude-code -yFügen Sie den kopierten Befehl in ein Terminal ein. Er installiert diese SKILL.md in dem jeweiligen Agenten.
npx skills add AThevon/genjutsu --skill design-audit -a codex -yFügen Sie den kopierten Befehl in ein Terminal ein. Er installiert diese SKILL.md in dem jeweiligen Agenten.
npx skills add AThevon/genjutsu --skill design-audit -a grok -ySenden Sie die kopierte Nachricht in einem Grok Bot-Chat. Der Bot ruft diese SKILL.md von GitHub ab und fügt sie den Skills hinzu, die alle Ihre Bots gemeinsam nutzen.
Install this skill: https://github.com/AThevon/genjutsu/tree/HEAD/skills/_jutsu/design-auditVom Herausgeber
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.
The final checkpoint. Loaded by
/genjutsu:paintat the end of the pipeline. Scans the codebase for motion gaps, a11y violations, perf issues, and inconsistencies.
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:
file:line and the
matched text, so you report the evidence rather than a verdict.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:
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.
Pick the subsection matching the project stack.
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.Modifier.recomposeHighlighter in androidx - it is a sample you vendor into a debug source set.BaselineProfileGenerator) for production builds.Modifier.semantics is set on custom components (TalkBack support)..accessibilityLabel / .accessibilityHint on every interactive view.Environment Overrides in Xcode).Structure findings by severity:
prefers-reduced-motion handlingoutline: none without :focus-visible replacementAnimatePresencearia-hidden on decorative animationssetTimeout used for animation loopswill-change usageDesign audit checklist - motion gaps, accessibility, color consistency, responsive, performance.
---name: design-auditdescription: Design audit checklist - motion gaps, accessibility, color consistency, responsive, performance.---# skills/_jutsu/design-audit/SKILL.mdFAQ
Laden Sie skills/_jutsu/design-audit/SKILL.md vom Herausgeber herunter oder kopieren Sie den Pfad und öffnen Sie das Repository. PlugMCP listet den Skill und hostet die Datei nicht.
Der Herausgeber pflegt es unter https://github.com/AThevon/genjutsu.
Claude, Cursor, Codex und Grok Build können eine SKILL.md lesen, die Sie aus dem Repository des Herausgebers hinzufügen. Grok Bot installiert sie, wenn Sie den Link zum GitHub-Ordner des Skills in einem Chat senden.