1---
  2name: audit
  3description: Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
  4version: 2.1.1
  5---
  6
  7## MANDATORY PREPARATION
  8
  9Invoke /impeccable — it contains design principles, anti-patterns, and the **Context Gathering Protocol**. Follow the protocol before proceeding — if no design context exists yet, you MUST run /impeccable teach first.
 10
 11---
 12
 13Run systematic **technical** quality checks and generate a comprehensive report. Don't fix issues — document them for other commands to address.
 14
 15This is a code-level audit, not a design critique. Check what's measurable and verifiable in the implementation.
 16
 17## Diagnostic Scan
 18
 19Run comprehensive checks across 5 dimensions. Score each dimension 0-4 using the criteria below.
 20
 21### 1. Accessibility (A11y)
 22
 23**Check for**:
 24- **Contrast issues**: Text contrast ratios < 4.5:1 (or 7:1 for AAA)
 25- **Missing ARIA**: Interactive elements without proper roles, labels, or states
 26- **Keyboard navigation**: Missing focus indicators, illogical tab order, keyboard traps
 27- **Semantic HTML**: Improper heading hierarchy, missing landmarks, divs instead of buttons
 28- **Alt text**: Missing or poor image descriptions
 29- **Form issues**: Inputs without labels, poor error messaging, missing required indicators
 30
 31**Score 0-4**: 0=Inaccessible (fails WCAG A), 1=Major gaps (few ARIA labels, no keyboard nav), 2=Partial (some a11y effort, significant gaps), 3=Good (WCAG AA mostly met, minor gaps), 4=Excellent (WCAG AA fully met, approaches AAA)
 32
 33### 2. Performance
 34
 35**Check for**:
 36- **Layout thrashing**: Reading/writing layout properties in loops
 37- **Expensive animations**: Animating layout properties (width, height, top, left) instead of transform/opacity
 38- **Missing optimization**: Images without lazy loading, unoptimized assets, missing will-change
 39- **Bundle size**: Unnecessary imports, unused dependencies
 40- **Render performance**: Unnecessary re-renders, missing memoization
 41
 42**Score 0-4**: 0=Severe issues (layout thrash, unoptimized everything), 1=Major problems (no lazy loading, expensive animations), 2=Partial (some optimization, gaps remain), 3=Good (mostly optimized, minor improvements possible), 4=Excellent (fast, lean, well-optimized)
 43
 44### 3. Theming
 45
 46**Check for**:
 47- **Hard-coded colors**: Colors not using design tokens
 48- **Broken dark mode**: Missing dark mode variants, poor contrast in dark theme
 49- **Inconsistent tokens**: Using wrong tokens, mixing token types
 50- **Theme switching issues**: Values that don't update on theme change
 51
 52**Score 0-4**: 0=No theming (hard-coded everything), 1=Minimal tokens (mostly hard-coded), 2=Partial (tokens exist but inconsistently used), 3=Good (tokens used, minor hard-coded values), 4=Excellent (full token system, dark mode works perfectly)
 53
 54### 4. Responsive Design
 55
 56**Check for**:
 57- **Fixed widths**: Hard-coded widths that break on mobile
 58- **Touch targets**: Interactive elements < 44x44px
 59- **Horizontal scroll**: Content overflow on narrow viewports
 60- **Text scaling**: Layouts that break when text size increases
 61- **Missing breakpoints**: No mobile/tablet variants
 62
 63**Score 0-4**: 0=Desktop-only (breaks on mobile), 1=Major issues (some breakpoints, many failures), 2=Partial (works on mobile, rough edges), 3=Good (responsive, minor touch target or overflow issues), 4=Excellent (fluid, all viewports, proper touch targets)
 64
 65### 5. Anti-Patterns (CRITICAL)
 66
 67Check against ALL the **DON'T** guidelines in the impeccable skill. Look for AI slop tells (AI color palette, gradient text, glassmorphism, hero metrics, card grids, generic fonts) and general design anti-patterns (gray on color, nested cards, bounce easing, redundant copy).
 68
 69**Score 0-4**: 0=AI slop gallery (5+ tells), 1=Heavy AI aesthetic (3-4 tells), 2=Some tells (1-2 noticeable), 3=Mostly clean (subtle issues only), 4=No AI tells (distinctive, intentional design)
 70
 71## Generate Report
 72
 73### Audit Health Score
 74
 75| # | Dimension | Score | Key Finding |
 76|---|-----------|-------|-------------|
 77| 1 | Accessibility | ? | [most critical a11y issue or "--"] |
 78| 2 | Performance | ? | |
 79| 3 | Responsive Design | ? | |
 80| 4 | Theming | ? | |
 81| 5 | Anti-Patterns | ? | |
 82| **Total** | | **??/20** | **[Rating band]** |
 83
 84**Rating bands**: 18-20 Excellent (minor polish), 14-17 Good (address weak dimensions), 10-13 Acceptable (significant work needed), 6-9 Poor (major overhaul), 0-5 Critical (fundamental issues)
 85
 86### Anti-Patterns Verdict
 87**Start here.** Pass/fail: Does this look AI-generated? List specific tells. Be brutally honest.
 88
 89### Executive Summary
 90- Audit Health Score: **??/20** ([rating band])
 91- Total issues found (count by severity: P0/P1/P2/P3)
 92- Top 3-5 critical issues
 93- Recommended next steps
 94
 95### Detailed Findings by Severity
 96
 97Tag every issue with **P0-P3 severity**:
 98- **P0 Blocking**: Prevents task completion — fix immediately
 99- **P1 Major**: Significant difficulty or WCAG AA violation — fix before release
100- **P2 Minor**: Annoyance, workaround exists — fix in next pass
101- **P3 Polish**: Nice-to-fix, no real user impact — fix if time permits
102
103For each issue, document:
104- **[P?] Issue name**
105- **Location**: Component, file, line
106- **Category**: Accessibility / Performance / Theming / Responsive / Anti-Pattern
107- **Impact**: How it affects users
108- **WCAG/Standard**: Which standard it violates (if applicable)
109- **Recommendation**: How to fix it
110- **Suggested command**: Which command to use (prefer: /animate, /quieter, /shape, /optimize, /adapt, /clarify, /layout, /distill, /delight, /audit, /harden, /polish, /bolder, /typeset, /critique, /colorize, /overdrive)
111
112### Patterns & Systemic Issues
113
114Identify recurring problems that indicate systemic gaps rather than one-off mistakes:
115- "Hard-coded colors appear in 15+ components, should use design tokens"
116- "Touch targets consistently too small (<44px) throughout mobile experience"
117
118### Positive Findings
119
120Note what's working well — good practices to maintain and replicate.
121
122## Recommended Actions
123
124List recommended commands in priority order (P0 first, then P1, then P2):
125
1261. **[P?] `/command-name`** — Brief description (specific context from audit findings)
1272. **[P?] `/command-name`** — Brief description (specific context)
128
129**Rules**: Only recommend commands from: /animate, /quieter, /shape, /optimize, /adapt, /clarify, /layout, /distill, /delight, /audit, /harden, /polish, /bolder, /typeset, /critique, /colorize, /overdrive. Map findings to the most appropriate command. End with `/polish` as the final step if any fixes were recommended.
130
131After presenting the summary, tell the user:
132
133> You can ask me to run these one at a time, all at once, or in any order you prefer.
134>
135> Re-run `/audit` after fixes to see your score improve.
136
137**IMPORTANT**: Be thorough but actionable. Too many P3 issues creates noise. Focus on what actually matters.
138
139**NEVER**:
140- Report issues without explaining impact (why does this matter?)
141- Provide generic recommendations (be specific and actionable)
142- Skip positive findings (celebrate what works)
143- Forget to prioritize (everything can't be P0)
144- Report false positives without verification
145
146Remember: You're a technical quality auditor. Document systematically, prioritize ruthlessly, cite specific code locations, and provide clear paths to improvement.