Audit
Generate a scored technical quality report—accessibility, performance, theming, responsive layout, and anti-patterns—with P0–P3 severities without auto-fixing code.
Overview
Audit is an agent skill most often used in Ship (also Ship review, Operate iterate) that scores five technical quality dimensions and outputs a P0–P3 actionable plan without applying fixes.
Install
npx skills add https://github.com/pbakaus/impeccable --skill auditWhat is this skill?
- Mandatory /impeccable prep and Context Gathering Protocol; requires teach when design context is missing
- Five diagnostic dimensions each scored 0–4: accessibility, performance, theming, responsive design, anti-patterns
- Code-level verification—contrast ratios, ARIA, keyboard order, semantic HTML—not design taste review
- P0–P3 severity ratings with actionable plan; documents issues for other commands instead of fixing
- Explicitly not a design critique—pair with critique for UX judgment
- 5 diagnostic dimensions each scored 0–4
- P0–P3 severity ratings in the actionable plan
Adoption & trust: 82.6k installs on skills.sh; 35.9k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are about to ship UI but lack a structured, severity-ranked technical report for a11y, performance, and responsive implementation.
Who is it for?
Indie builders with frontend code in repo who need a pre-release or regression technical gate aligned to Impeccable anti-patterns.
Skip if: Pure UX hierarchy or emotional design reviews—use critique; not a substitute for full penetration testing or backend load testing unless covered in your run.
When should I use this skill?
User wants an accessibility check, performance audit, or technical quality review.
What do I get? / Deliverables
You get a scored multi-dimension audit document with P0–P3 items and an actionable plan for other commands or your agent to fix—after Impeccable context is ready.
- Comprehensive scored audit report across five dimensions
- P0–P3 prioritized issue list
- Actionable remediation plan for downstream fixes
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Ship is where measurable quality gates belong before you release or iterate in production. Testing subphase fits systematic diagnostic scans and severity-ranked findings rather than subjective UX critique.
Where it fits
Score five dimensions on a checkout flow before tagging a release.
Produce a P0–P3 backlog after a large CSS refactor without auto-patching.
Re-run diagnostics after user-reported keyboard trap on settings.
Baseline technical debt on a new dashboard module mid-build.
How it compares
Code-level checker with 0–4 dimension scores; critique handles blind UX assessment, audit handles measurable implementation defects.
Common Questions / FAQ
Who is audit for?
Solo builders shipping web UI who want Impeccable-backed technical checks documented with severities instead of silent auto-fixes.
When should I use audit?
In Ship/testing before release; in Ship/review after large UI changes; in Operate/iterate when regressions appear—after Impeccable context (teach if missing).
Is audit safe to install?
It may read project files and run checks; review the Security Audits panel on this Prism page and validate what your agent executes locally.
Workflow Chain
Requires first: impeccable, impeccable teach
SKILL.md
READMESKILL.md - Audit
## MANDATORY PREPARATION Invoke /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. --- Run systematic **technical** quality checks and generate a comprehensive report. Don't fix issues — document them for other commands to address. This is a code-level audit, not a design critique. Check what's measurable and verifiable in the implementation. ## Diagnostic Scan Run comprehensive checks across 5 dimensions. Score each dimension 0-4 using the criteria below. ### 1. Accessibility (A11y) **Check for**: - **Contrast issues**: Text contrast ratios < 4.5:1 (or 7:1 for AAA) - **Missing ARIA**: Interactive elements without proper roles, labels, or states - **Keyboard navigation**: Missing focus indicators, illogical tab order, keyboard traps - **Semantic HTML**: Improper heading hierarchy, missing landmarks, divs instead of buttons - **Alt text**: Missing or poor image descriptions - **Form issues**: Inputs without labels, poor error messaging, missing required indicators **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) ### 2. Performance **Check for**: - **Layout thrashing**: Reading/writing layout properties in loops - **Expensive animations**: Animating layout properties (width, height, top, left) instead of transform/opacity - **Missing optimization**: Images without lazy loading, unoptimized assets, missing will-change - **Bundle size**: Unnecessary imports, unused dependencies - **Render performance**: Unnecessary re-renders, missing memoization **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) ### 3. Theming **Check for**: - **Hard-coded colors**: Colors not using design tokens - **Broken dark mode**: Missing dark mode variants, poor contrast in dark theme - **Inconsistent tokens**: Using wrong tokens, mixing token types - **Theme switching issues**: Values that don't update on theme change **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) ### 4. Responsive Design **Check for**: - **Fixed widths**: Hard-coded widths that break on mobile - **Touch targets**: Interactive elements < 44x44px - **Horizontal scroll**: Content overflow on narrow viewports - **Text scaling**: Layouts that break when text size increases - **Missing breakpoints**: No mobile/tablet variants **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) ### 5. Anti-Patterns (CRITICAL) Check 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). **Score 0-4**: 0=AI slop gallery (5+ tells),