skills/i-audit/SKILL.md
Use when the user says: "audit this UI", "frontend quality", "full UI audit", "design audit". Comprehensive audit of interface quality across accessibility, performance, theming, and responsive design.
npx skillsauth add NodeJSmith/Claudefiles i-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.
Run systematic quality checks and generate a comprehensive audit report with prioritized issues and actionable recommendations. Don't fix issues - document them for other commands to address.
Read ~/.claude/skills/i-frontend-design/SKILL.md for design principles and anti-patterns. Check for design context (design/context.md, .impeccable.md, or design/direction.md) — if found, use it to inform brand-specific judgments. If no context exists, proceed anyway but note in the report: "No design context found — anti-pattern checks are universal only; brand-specific judgments may not apply. Run /i-teach-impeccable to establish context."
Audits are read-only diagnostics — they should never be blocked by missing context.
Run comprehensive checks across multiple dimensions:
Accessibility (A11y) - Check for:
Performance - Check for:
Theming - Check for:
Responsive Design - Check for:
Anti-Patterns (CRITICAL) - Check against the anti-patterns reference. Look for AI slop tells and general design anti-patterns documented there.
CRITICAL: This is an audit, not a fix. Document issues thoroughly with clear explanations of impact. Use other commands (polish, optimize, harden, etc.) to fix issues after audit.
Create a detailed audit report with the following structure:
Start here. Pass/fail: Does this look AI-generated? List specific tells from the anti-patterns reference. Be brutally honest.
For each issue, document:
/i-colorize/i-layout/i-typeset/i-animate/i-optimize/i-adapt/i-polish/i-harden/i-clarify/i-quieter/i-bolder/i-polish[Issues that block core functionality or violate WCAG A]
[Significant usability/accessibility impact, WCAG AA violations]
[Quality issues, WCAG AAA violations, performance concerns]
[Minor inconsistencies, optimization opportunities]
Identify recurring problems:
Note what's working well:
Create actionable plan:
Group findings by the skill that would fix them, using the routing from the per-finding "Suggested command" field. Example:
/i-polish to align with design system (addresses N theming issues)"/i-adapt to fix responsive problems (addresses N mobile/touch issues)"/i-harden to improve resilience (addresses N edge cases)"IMPORTANT: Be thorough but actionable. Too many low-priority issues creates noise. Focus on what actually matters.
NEVER:
Remember: You're a quality auditor with exceptional attention to detail. Document systematically, prioritize ruthlessly, and provide clear paths to improvement. A good audit makes fixing easy.
Run get-skill-tmpdir i-audit and write the audit report to <tmpdir>/audit-YYYY-MM-DD.md. Then summarize in conversation:
development
Use when the user says: 'create an issue', 'file an issue', 'open an issue', 'write an issue', 'new issue for this'. Codebase-aware issue creation — investigates the code to produce well-structured issues with acceptance criteria, affected areas, and enough detail for automated triage.
development
Use when the user says: 'triage issues', 'classify issues by complexity', 'assess issue complexity', 'find quick wins', 'which issues are small', 'batch issue assessment'. Batch codebase-aware issue triage — parallel Haiku subagents assess actual complexity and effort by reading the code, not just titles.
development
Use when the user says: "review my changes", "run the reviewers", "code and integration review", "readability review", "maintainability review", "sniff test this", "WTF check", "code smells", "is this code any good", "fresh eyes on this branch", "review this directory", "check this module". Dispatches three parallel reviewers — code, integration, and a readability pass — and consolidates findings into one prioritized report.
development
Use when the user says: "clean code check", "style review", "LLM smell check", "code hygiene", "nitpick this", "style check", "find style sins", "nitpicker review", "anal retentive review", "exhaustive style review", "no-filter style report". Dispatches three parallel stylistic checkers — llm-checker (training-bias patterns), lazy-checker (deferred debt), and nitpicker (style hygiene) — and consolidates findings into a report organized by checker with a Summary section for orchestration consumption.