Accessibility Audit

WCAG 2.1 AA audit across all 4 principles with P0-P3 severity and a remediation plan

Tested · Works

Test report

Verdict
Tested · Works
Score
9.2/10
Tested
Jul 21, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Aug 10, 2026 · ba3210b

⚠ The author changed this skill after we tested it. The verdict below describes the version we ran on Jul 21, 2026; it's queued for a re-test.

Located SKILL.md at skills/accessibility-audit/ (a build copy also exists under dist/pi/.agents/skills/). All 3 body-referenced reference files fetch HTTP 200; frontmatter parses with name+description; pure markdown, no scripts or hardcoded paths, no security smells. Verified clone+copy install in a mktemp HOME: SKILL.md and references/ landed at ~/.claude/skills/accessibility-audit/. Trigger 5/5 — SHOULD: "run a WCAG accessibility audit on our checkout flow" / "we got an ADA demand letter, find and fix the accessibility issues" / "test this page for keyboard navigation and screen reader support"; SHOULD NOT: "add a dark mode toggle to my settings page" (build task) / "review my code for security vulnerabilities" (audit but not a11y). Output: audited one signup.html with real defects two ways. Baseline was a flat 9-bullet list ("looks like low contrast. Should be checked"); skill version quantified contrast (2.5:1 vs 4.5:1, cited 1.4.3 AA), bucketed P0-P3 with counts, mapped every finding to a specific WCAG success criterion, and caught two issues baseline missed (4.1.3 live-region status message on the modal, 3.3.2 error-correction guidance). Scored 8: clearly richer and better-triaged, same core bug set.

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 8/10
  • Docs & honesty 5/5

What Accessibility Audit does

A methodology skill that runs a WCAG 2.1 AA accessibility audit organized by the four principles (perceivable, operable, understandable, robust), classifies findings into P0-P3 severity, and produces a structured audit report plus a sequenced remediation roadmap. Triggers when the user asks for an accessibility or WCAG/a11y audit, ADA/Section 508 compliance review, keyboard or screen-reader testing, or systematic remediation of reported accessibility issues. Stack-agnostic and ships three reference files (WCAG quick reference, ARIA patterns, report template).

How to install Accessibility Audit

git clone --depth 1 https://github.com/rampstackco/claude-skills.git /tmp/accessibility-audit-src
mkdir -p ~/.claude/skills
cp -R /tmp/accessibility-audit-src/skills/accessibility-audit ~/.claude/skills/accessibility-audit
# Pure-markdown skill: SKILL.md + references/{wcag-quick-reference,aria-patterns,audit-report-template}.md
# No dependencies, no scripts, no API keys required.
# The methodology optionally references external tools you run yourself (not installed here):
#   axe DevTools / Lighthouse / WAVE browser extensions, Pa11y CLI, and a screen reader (VoiceOver/NVDA/JAWS).

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

Commands — how to trigger Accessibility Audit

  • /accessibility-audit WCAG 2.1 AA audit across all 4 principles with P0-P3 severity and a remediation plan

It also activates on plain-language prompts like these:

  • Audit our site for WCAG compliance
  • Prepare an accessibility report before certification
  • Fix keyboard navigation issues on this page

Frequently asked questions

Is the Accessibility Audit skill free?
Yes. The skill itself is free from rampstackco/claude-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Accessibility Audit work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Located SKILL.md at skills/accessibility-audit/ (a build copy also exists under dist/pi/.agents/skills/). All 3 body-referenced reference files fetch HTTP 200; frontmatter parses with name+description; pure markdown, no scripts or hardcoded paths, no security smells. Verified clone+copy install in a mktemp HOME: SKILL.md and references/ landed at ~/.claude/skills/accessibility-audit/. Trigger 5/5 — SHOULD: "run a WCAG accessibility audit on our checkout flow" / "we got an ADA demand letter, find and fix the accessibility issues" / "test this page for keyboard navigation and screen reader support"; SHOULD NOT: "add a dark mode toggle to my settings page" (build task) / "review my code for security vulnerabilities" (audit but not a11y). Output: audited one signup.html with real defects two ways. Baseline was a flat 9-bullet list ("looks like low contrast. Should be checked"); skill version quantified contrast (2.5:1 vs 4.5:1, cited 1.4.3 AA), bucketed P0-P3 with counts, mapped every finding to a specific WCAG success criterion, and caught two issues baseline missed (4.1.3 live-region status message on the modal, 3.3.2 error-correction guidance). Scored 8: clearly richer and better-triaged, same core bug set.
What is the Accessibility Audit SkillProof Score?
9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Accessibility 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 Accessibility 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.