Is the A11y Audit skill free?

Yes. The skill itself is free from plugin87/ux-ui-agent-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the A11y Audit SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install A11y Audit?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use A11y Audit with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

A11y Audit

WCAG 2.2 AA/AAA audit with measured contrast ratios and criterion-referenced fixes

by plugin87 · plugin87/ux-ui-agent-skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 90ded62

Fetched SKILL.md and spot-checked 6 referenced paths via raw fetch — all HTTP 200; wcag-checklist.md and aria-patterns.md are substantial real references (POUR-organized criteria table, ARIA APG keyboard maps). Ran scripts/contrast.py (pure python3, no deps): #767676/#fff = 4.54:1 PASS, #999/#fff = 2.85:1 FAIL, exit codes correct. For the output test I wrote a 6-element card.html and audited it two ways: a baseline eyeball audit vs the skill body, which mandates running contrast.py per pair. Measured ratios flipped two eyeball judgments — the blue link #5b8def looks fine but measures 3.23:1 (FAIL 1.4.3) and the red badge #d32f2f looks weak but measures 4.98:1 (PASS); #8a8a8a heading = 3.45:1 and #a0a0a0 text = 2.61:1 both FAIL. No security smells (no curl|sh, base64, eval). Friction: skill dir bundles only SKILL.md and depends on repo-root sibling files/scripts, so a standalone skill-dir copy breaks its steps — full package install needed.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 4/5

What A11y Audit does

Audits a UI or component against WCAG 2.2 AA/AAA and WAI-ARIA patterns, returning a findings table keyed to specific success criteria with P0/P1/P2 severity and concrete fixes. Triggers when the user asks for an accessibility check, contrast verification, or keyboard/screen-reader review. It reads a POUR-organized checklist and ARIA reference and measures color contrast with a bundled script rather than eyeballing ratios.

How to install A11y Audit

git clone --depth 1 https://github.com/plugin87/ux-ui-agent-skills.git /tmp/a11y-audit-src
mkdir -p ~/.claude/skills
cp -R /tmp/a11y-audit-src/.claude/skills/a11y-audit ~/.claude/skills/a11y-audit
# IMPORTANT: the skill dir holds only SKILL.md. Its steps read repo-root sibling files
#   accessibility/wcag-checklist.md, accessibility/aria-patterns.md, taste/motion-choreography.md
#   and run scripts/contrast.py, scripts/measure_render.mjs, scripts/verify_states.mjs
# — all relative to the repo root, NOT bundled with the skill. For full function, install the
# whole package into your project: npx ux-ui-agent-skills  (installs accessibility/ + scripts/ too).
# scripts/contrast.py = pure python3, no deps. measure_render.mjs/verify_states.mjs need:
#   npm i -D playwright   (without it they SKIP with exit 0, they do not error).

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger A11y Audit

/a11y-audit WCAG 2.2 AA/AAA audit with measured contrast ratios and criterion-referenced fixes

It also activates on plain-language prompts like these:

Audit this page for WCAG 2.2 AA compliance
Check the contrast ratios on this design
Review this component for screen-reader support

Frequently asked questions

Is the A11y Audit skill free?: Yes. The skill itself is free from plugin87/ux-ui-agent-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does A11y Audit work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md and spot-checked 6 referenced paths via raw fetch — all HTTP 200; wcag-checklist.md and aria-patterns.md are substantial real references (POUR-organized criteria table, ARIA APG keyboard maps). Ran scripts/contrast.py (pure python3, no deps): #767676/#fff = 4.54:1 PASS, #999/#fff = 2.85:1 FAIL, exit codes correct. For the output test I wrote a 6-element card.html and audited it two ways: a baseline eyeball audit vs the skill body, which mandates running contrast.py per pair. Measured ratios flipped two eyeball judgments — the blue link #5b8def looks fine but measures 3.23:1 (FAIL 1.4.3) and the red badge #d32f2f looks weak but measures 4.98:1 (PASS); #8a8a8a heading = 3.45:1 and #a0a0a0 text = 2.61:1 both FAIL. No security smells (no curl|sh, base64, eval). Friction: skill dir bundles only SKILL.md and depends on repo-root sibling files/scripts, so a standalone skill-dir copy breaks its steps — full package install needed.
What is the A11y Audit SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install A11y Audit?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use A11y Audit with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.