skills/ui-audit/SKILL.md
Audits web UI quality across accessibility, interaction, forms, typography, navigation, layout, performance, motion, and microcopy. Covers alt text, data-table semantics, captions and transcripts, document language, reduced motion, lazy loading, script loading, and resource hints. Use when reviewing or refining frontend UI before merge or release, asking "check my UI", "is this accessible", "polish this page", "respect reduced motion", or when the user asks for a UI, UX, or accessibility audit.
npx skillsauth add mblode/agent-skills ui-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Final-pass audit workflow for web interfaces. Focuses on concrete issues with concrete fixes.
Use this skill when:
Copy and track this checklist during the audit:
Audit progress:
- [ ] Step 1: Scope changed surfaces and select relevant categories
- [ ] Step 2: Run CRITICAL checks first (a11y, interaction, forms)
- [ ] Step 3: Run HIGH/MEDIUM checks for the same surfaces
- [ ] Step 4: Report findings with file:line and concrete fixes
- [ ] Step 5: Re-check touched files and mark passes
CRITICAL and HIGH findings before medium-priority polish.ui-animation for timing, easing, gesture, and review details.craft-checklist.md before reporting.| Priority | Category | Impact | Prefix |
|----------|----------|--------|--------|
| 1 | Accessibility and Semantics | CRITICAL | a11y- |
| 2 | Keyboard and Interaction | CRITICAL | interaction- |
| 3 | Forms and Validation | CRITICAL | forms- |
| 4 | Typography and Readability | HIGH | type- |
| 5 | Navigation and Feedback | HIGH | nav- |
| 6 | Layout and Resilience | HIGH | layout- |
| 7 | Performance and Visual Stability | HIGH | perf- |
| 8 | Motion and Theme Behavior | HIGH | motion- |
| 9 | Content and Microcopy | MEDIUM | copy- |
Read only what is needed for the current audit scope:
rules/_sections.mdrules/<prefix>-*.mdcraft-checklist.mdtypography-checklist.mdExample rule files:
rules/a11y-semantic-html-first.md
rules/forms-inline-errors-first-focus.md
rules/perf-image-dimensions-and-priority.md
Each rule file contains:
Report findings in this format:
## UI Audit Findings
### path/to/file.tsx
- [CRITICAL] `a11y-icon-controls-labeled`: Icon button is missing an accessible name.
- Fix: Add `aria-label="Close dialog"` (or visible text label).
### path/to/clean-file.tsx
- ✓ pass
file:line when line numbers are available.✓ pass.rules/<prefix>-*.md).rules/; if no rule fits, describe the issue without an id.CRITICAL categories (a11y, interaction, forms) to reach visual polish faster. The priority order in the rule-category table is load-bearing.✓ pass means the file was actually read against the loaded rules, not assumed clean.craft-checklist.md apply to UI code being audited, not to this skill's execution — do not mix the two when reporting findings.development
Reverse-engineers a UI animation from a screen recording — extracts frames, tracks motion per frame, fits easing and spring curves, annotates choreography, and emits CSS, Motion/Framer Motion, SwiftUI, React Native, or UIKit code. Use when the user shares or uploads a screen recording or video of a UI animation, or asks to "reverse engineer this animation", "recreate this animation", "match this easing", "extract the animation curve", "figure out the spring from this video", "copy this transition from a video", "how does this animation work", or "reproduce this motion".
development
Produces a read-only review report of the current local diff or branch — it lists findings and does NOT edit files. Use when asked to run `/pr-reviewer` before commit, before push, or before handing changes off for PR creation or update; also use for "review my changes", "code review", "code quality review", or when you want findings listed by severity so you can decide what to fix yourself. Also use for "thermo-nuclear review", "deep code quality audit", "structural review", "harsh maintainability review", or "code judo" — these load the structural quality rubric for an unusually strict maintainability pass. Also use for "deslop this", "clean up AI code", "remove slop", or "review for AI patterns" — these load the AI slop detection catalog. For automatic fix-in-place (no manual review step needed), use the private `simplify` skill instead.
development
Autonomous PR monitor — polls every 2 minutes for merge conflicts, CI/CD failures across GitHub Actions, Buildkite, Vercel, and Fly.io, review comments, and merge readiness. Auto-detects PR from current branch, fixes what it can, notifies on state changes. No setup questions. Also runs as one-shot for specific concerns. Use when asked to babysit a PR, watch a PR, monitor CI, keep a PR green, handle merge conflicts, poll PR status, run `/pr-babysitter`, fix CI, diagnose CI failure, why is CI red, CI is broken, loop on CI, fix CI checks, resolve merge conflicts, or fix conflicts.
development
Feature-level UX audit for React/Next.js code. Catches what Lighthouse, axe, ESLint, and Storybook miss — state coverage gaps (missing loading/empty/error), form data loss on validation, broken focus management, optimistic UI without rollback, skeleton-induced layout shift, vague microcopy, and 25+ other modern frontend UX bugs. Diff-aware (audits changed files only) and produces a 3-tier ship-readiness verdict (release-blocker / fix-this-sprint / backlog) grouped by surface, with concrete fixes using modern React 19 APIs (useActionState, useFormStatus, useOptimistic, useTransition, Suspense). Use before merging a frontend PR, before shipping a feature, or when asked "is this checkout/onboarding/dashboard ready?", "review this PR for UX bugs", "audit this component", "what would break in production?", "is this ready to ship?"