agentleFS
GlamgarOnDiscordGlamgarOnDiscord/claude-saas-blueprint/.claude/skills/ui-audit/SKILL.md

ui-audit

Skill2 starsChanged 6 months agoMITView on GitHub

Audit UX/UI read-only — WCAG 2.2 AA, heuristiques Nielsen, anti-slop. Aucun changement de code, rapport file:line.

13 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use browse and ux-audit.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CodeWithBehnamSkill

    browse

    Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence.

    Also in 4 projects that use this

  • shmehroSkill

    ux-audit

    Perform a heuristic UX audit on a UI screen, flow, or component description

    Also in 3 projects that use this

The file

Files
SKILL.md

UI Audit — Read-only

Role

Auditeur UX senior. Ce skill ne modifie jamais le code — il produit un rapport prioritise.

Ce que fait ce skill

  • Audit conformite WCAG 2.2 AA (contraste, semantique, ARIA, focus, target size, reduced motion)
  • Evaluation des 10 heuristiques de Nielsen
  • Detection des patterns anti-slop (UI generique generee par IA)
  • Verification des etats : loading / empty / error / success
  • Rapport file:line avec severite

Ce que ce skill NE fait PAS

  • Modifier du code
  • Generer de la nouvelle UI
  • Proposer des implementations specifiques (uniquement le probleme et l'outcome attendu)

Process

1. Scan

Lire le ou les fichiers cibles. Si l'utilisateur ne precise rien, demander quel scope auditer.

2. WCAG 2.2 AA

  • Contraste : ratio body >= 4.5:1, large text >= 3:1, UI components >= 3:1
  • HTML semantique : <main>, <nav>, <section aria-label>, headings hierarchiques
  • Focus visible sur tous les elements interactifs (focus-visible:ring)
  • Target size minimum 24x24px (44x44 ideal mobile)
  • prefers-reduced-motion respecte sur les animations
  • Images : alt non vide pour les images informatives, alt="" pour decoratives
  • Formulaires : <label> lie a chaque input

3. Heuristiques Nielsen

  1. Visibilite du statut systeme (loading, succes, erreur)
  2. Correspondance avec le monde reel (vocabulaire utilisateur)
  3. Controle et liberte utilisateur (back, undo, cancel)
  4. Coherence et standards
  5. Prevention des erreurs (validation avant submit)
  6. Reconnaissance plutot que rappel
  7. Flexibilite et efficacite (raccourcis pour power users)
  8. Design minimaliste
  9. Aide a reconnaitre, diagnostiquer, recuperer (messages d'erreur)
  10. Aide et documentation contextuelle

4. Anti-slop

  • Hero centre avec 3 cards egales
  • Inter / Roboto / Arial / Space Grotesk
  • Numeros ronds (50%, 1000+)
  • Gradient de fond purple-blue
  • Spinner au lieu de Skeleton
  • shadcn par defaut sans customisation
  • Glassmorphism sur tout
  • Emojis dans le code

5. Etats manquants

Pour chaque composant interactif, verifier :

  • Loading state (Skeleton)
  • Empty state (avec CTA pour creer le premier element)
  • Error state (message clair + action de retry)
  • Success state si applicable

Format du rapport

## UI Audit Report — [date]

### Summary
- WCAG AA violations : X
- Anti-slop patterns : X
- Missing states : X
- Nielsen concerns : X

### Critical (must fix avant ship)
- `path/file.tsx:42` — [WCAG 1.4.3] Contrast 2.1:1 sur body text (need 4.5:1)
- `path/file.tsx:87` — [Nielsen #1] Pas de loading state sur fetch async

### Warning (should fix)
- `path/file.tsx:15` — [anti-slop] Hero centre avec 3 cards egales
- `path/file.tsx:103` — [WCAG 2.4.7] Pas de focus visible sur le bouton

### Info (nice to fix)
- `path/file.tsx:200` — [Nielsen #1] Loading repose sur spinner ; preferer Skeleton sans CLS
- `path/file.tsx:220` — [Nielsen #7] Pas de raccourci clavier pour les power users

### Score
- WCAG : X/10
- UX : X/10
- Anti-slop : X/10

References

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.