dot_agents/skills/audit/SKILL.md
Perform comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates detailed report of issues with severity ratings and recommendations.
npx skillsauth add kevin-mok/ai-cli-dotfiles 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.
First: Use the frontend-design skill for design principles and anti-patterns.
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 ALL the DON'T guidelines in the frontend-design 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).
CRITICAL: This is an audit, not a fix. Document issues thoroughly with clear explanations of impact. Use other commands (normalize, 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 skill's Anti-Patterns section. Be brutally honest.
For each issue, document:
[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:
Map issues to available commands. Prefer these: /normalize, /onboard, /polish, /animate, /clarify, /audit, /quieter, /typeset, /harden, /overdrive, /delight, /arrange, /critique, /colorize, /bolder, /optimize, /adapt, /distill, /extract. You may also suggest other installed skills you're sure exist, but never invent commands.
Examples:
/normalize to align with design system (addresses N theming issues)"/optimize to improve performance (addresses N performance issues)"/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.
testing
Use when asked to draft, write, prepare, open, update, or improve a pull request title or body from current branch changes, including base-branch comparisons, `docs/pr` sync, GitHub PR creation or editing with `gh`, DD/Cindy LessonOps handoffs, or reviewer-focused PR context.
tools
Improve typography by fixing font choices, hierarchy, sizing, weight consistency, and readability. Makes text feel intentional and polished.
content-media
Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.
documentation
One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.