Agent skill

Accessibility Audit

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

Audits a UI or design against WCAG 2.2 and ARIA patterns and returns findings with the criterion, severity and a specific fix for each.

MITAuto-check passedFrontend & Design

Install Accessibility Audit

skills CLI
$ npx skills add plugin87/ux-ui-agent-skills --skill a11y-audit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install plugin87/ux-ui-agent-skills a11y-audit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/plugin87/ux-ui-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/a11y-audit .claude/skills/a11y-audit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
a11y-audit
GitHub stars
1.5k
Token cost
~542 tokens
SKILL.md length
212 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

Audits a UI or design against WCAG 2.2 and ARIA patterns and returns findings with the criterion, severity and a specific fix for each.

  • Works in 5 steps: Read… → Check the mandatory P0 set per… → Verify WCAG 2.2 additions: Focus Not… → …
  • Checking a component or page for WCAG 2.2 conformance
  • SKILL.md covers Steps and Output
  • Calls npx, node and python3

What it does

The skill first checks that the surrounding kit, including its `tokens` folder, is installed. If only the skill folders are present, it says so, points you to `npx ux-ui-agent-skills init` or the plugin install, and stops rather than guessing at files it cannot open. It then reads the kit's WCAG checklist, organized by the POUR principles with P0, P1 and P2 priorities, and its ARIA patterns.

Each component gets the mandatory P0 checks: keyboard navigation, visible focus, screen-reader name, role and state, contrast of 4.5:1 for text and 3:1 for UI, a target size of at least 24×24 and no color-only signaling. It also covers the WCAG 2.2 additions Focus Not Obscured, Target Size and Accessible Authentication, and reduced-motion handling. Contrast is measured, not estimated, by running the kit's render and state scripts. The output is a findings table with passes confirmed explicitly.

When your agent uses it

  • Checking a component or page for WCAG 2.2 conformance
  • Verifying color contrast and focus states on rendered HTML
  • Reviewing keyboard and screen-reader behavior of a UI

Example prompts

  • “Audit the checkout form in ./src/checkout.html against WCAG 2.2 AA.”
  • “Measure the contrast of every text element in our dark theme.”
  • “Confirm that the modal component meets the POUR principles and list fixes.”

Requirements

  • The ux-ui-agent-skills kit installed, not only the skill folders
  • Node.js and Python 3 to run the contrast and render scripts

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Read ${CLAUDE_SKILL_DIR}/../../../accessibility/wcag-checklist.md (POUR-organized, P0/P1/P2) and…
  2. Check the mandatory P0 set per component: keyboard navigable, focus visible (≥3:1), screen-reader name/role/state, contrast (4.5:1 text /…
  3. Verify WCAG 2.2 additions: Focus Not Obscured (2.4.11), Target Size (2.5.8), Accessible Authentication (3.3.8).
  4. Contrast — measure, don't eyeball. For rendered HTML, RUN the real-render gates and report their actual output (CLAUDE.md → Verification…
  5. Check reduced-motion handling (${CLAUDE_SKILL_DIR}/../../../taste/motion-choreography.md).

What it can do on your machine

Read from SKILL.md and the folder at commit 14f8d44. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npx
    • node
    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Accessibility Audit loads about 542 tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 212 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~542

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from plugin87/ux-ui-agent-skills at commit 14f8d44, republished under its MIT licence (© plugin87). 212 words, ~542 tokens.

Download SKILL.mdSave it as .claude/skills/a11y-audit/SKILL.md (or your agent's skills folder).
name
a11y-audit
description
Audit a UI or design against WCAG 2.2 AA/AAA and ARIA patterns, returning criterion-referenced findings with severity and specific fixes. Use when the user wants an accessibility check, contrast verification, keyboard/screen-reader review, or wants to confirm a component meets POUR.

Skill: Accessibility Audit

Step 0 — is the kit here? This skill reads files from the kit. Check once: ls ${CLAUDE_SKILL_DIR}/../../../tokens >/dev/null 2>&1 && echo KIT_OK || echo KIT_MISSING On KIT_MISSING only the skill folders were installed, which is what npx skills add does. Say so plainly, point the user at npx ux-ui-agent-skills init or the plugin install, and stop. Do not guess the contents of a file you could not open.

Evaluate against WCAG 2.2 and the project's ARIA patterns.

Steps

  1. Read ${CLAUDE_SKILL_DIR}/../../../accessibility/wcag-checklist.md (POUR-organized, P0/P1/P2) and ${CLAUDE_SKILL_DIR}/../../../accessibility/aria-patterns.md.
  2. Check the mandatory P0 set per component: keyboard navigable, focus visible (≥3:1), screen-reader name/role/state, contrast (4.5:1 text / 3:1 UI), target size ≥24×24, no color-only signaling.
  3. Verify WCAG 2.2 additions: Focus Not Obscured (2.4.11), Target Size (2.5.8), Accessible Authentication (3.3.8).
  4. Contrast — measure, don't eyeball. For rendered HTML, RUN the real-render gates and report their actual output (CLAUDE.md → Verification Protocol): node ${CLAUDE_SKILL_DIR}/../../../scripts/measure_render.mjs <file> [--dark] (every text element) AND node ${CLAUDE_SKILL_DIR}/../../../scripts/verify_states.mjs <file> [--dark] (every interactive element in default/hover/focus — catches hover-state failures). For loose color pairs, python3 ${CLAUDE_SKILL_DIR}/../../../scripts/contrast.py "<fg>" "<bg>". Never state a ratio you did not measure.
  5. Check reduced-motion handling (${CLAUDE_SKILL_DIR}/../../../taste/motion-choreography.md).

Output

A findings table: WCAG criterion (e.g. 1.4.3) · severity (P0/P1/P2) · what fails · specific fix. Confirm passes explicitly. Accessibility may never be traded for aesthetics.

© plugin87, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/a11y-audit of plugin87/ux-ui-agent-skills.

Open the folder on GitHubat commit 14f8d44

Compare with similar skills

Accessibility Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Accessibility Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Accessibility Audit this skillplugin87/ux-ui-agent-skills1.5k—~542Automated safety check: PassMIT
Web Interface Guidelines Reviewervercel-labs/openreview1.7k98 repos~308Automated safety check: PassNone
Accessibility Reviewmarkmead/hyperui12k1 repos~1.1kAutomated safety check: PassMIT
Web Animation DesignbaptisteArno/typebot.io11k2 repos~2.7kAutomated safety check: PassCustom licence
Accessibility Fixeribelick/ui-skills9.4k4 repos~1.2kAutomated safety check: PassMIT
Wcag Audit PatternsvmDeshpande/ai-agent-automation17810 repos~610Automated safety check: PassApache-2.0

Similar skills

  • Web Interface Guidelines Reviewer

    vercel-labs/openreview

    Official

    Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my…

    1.7k GitHub starsUsed in 98 repos~308 tokens
    Frontend & DesignAuto-check passed
  • Accessibility Review

    markmead/hyperui

    Run a WCAG 2.1 AA accessibility audit on a design or page. An agent skill from markmead/hyperui.

    12k GitHub starsUsed in 1 repo~1.1k tokens
    Frontend & DesignAuto-check passed
  • Web Animation Design

    baptisteArno/typebot.io

    Guides easing, timing and animation choices for UI motion, based on a web animation course, and reviews existing animations in a before-and-after table.

    11k GitHub starsUsed in 2 repos~2.7k tokens
    Frontend & DesignAuto-check passed
  • Accessibility Fixer

    ibelick/ui-skills

    Audits and fixes HTML accessibility problems such as ARIA labels, keyboard navigation, focus management, contrast and form errors with minimal changes.

    9.4k GitHub starsUsed in 4 repos~1.2k tokens
    Frontend & DesignAuto-check passed
  • Wcag Audit Patterns

    vmDeshpande/ai-agent-automation

    Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance.

    178 GitHub starsUsed in 10 repos~610 tokens
    Frontend & DesignAuto-check passed
  • Baseline UI

    ibelick/ui-skills

    Applies a fixed set of UI rules for stack, components, interaction, animation, typography and layout, or reviews a file against them with concrete fixes.

    9.4k GitHub starsUsed in 8 repos~855 tokens
    Frontend & DesignAuto-check passed

More from plugin87/ux-ui-agent-skills

All 23 skills in this repo
  • Data-Dense Dashboard Designer

    plugin87/ux-ui-agent-skills

    Lays out dense analytics or trading-terminal screens in banded sections with hand-drawn SVG charts, instead of a wall of identical stat cards.

    1.5k GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • UI Component Spec Designer

    plugin87/ux-ui-agent-skills

    Writes a complete UI component spec with anatomy, variants, sizes, eight interaction states, design-token mapping and accessibility notes before or alongside code.

    1.5k GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Design Project Scaffold

    plugin87/ux-ui-agent-skills

    Creates a new design-product project from the kit's product-design template, then installs the engine folders and the Playwright dependency that the quality gates need.

    1.5k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Apply Aesthetic

    plugin87/ux-ui-agent-skills

    Applies a chosen visual direction, an archetype or one of 138 named design systems, by remapping design tokens, then checks contrast before it finishes.

    1.5k GitHub stars~597 tokensUpdated today
    Auto-check passed
  • Brand Kit Design Tokens

    plugin87/ux-ui-agent-skills

    Builds a from-scratch brand design system as three-tier DTCG tokens plus one theme.css with light and dark modes, checked against WCAG contrast rules.

    1.5k GitHub stars~809 tokensUpdated today
    Auto-check passed
  • Design Code for Any Framework

    plugin87/ux-ui-agent-skills

    Generates complete, accessible, token-driven UI component code for a chosen framework such as React with Tailwind, SwiftUI, Vue, Flutter or Jetpack Compose.

    1.5k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

Questions about Accessibility Audit

What does Accessibility Audit do?

Audits a UI or design against WCAG 2.2 and ARIA patterns and returns findings with the criterion, severity and a specific fix for each. The skill first checks that the surrounding kit, including its `tokens` folder, is installed. If only the skill folders are present, it says so, points you to `npx ux-ui-agent-skills init` or the plugin install, and stops rather than guessing at files it cannot open.

When should I use Accessibility Audit?

Accessibility Audit fits situations like: checking a component or page for WCAG 2.2 conformance; verifying color contrast and focus states on rendered HTML; reviewing keyboard and screen-reader behavior of a UI.

How do I install Accessibility Audit in Claude Code?

Run `npx skills add plugin87/ux-ui-agent-skills --skill a11y-audit -a claude-code`. Or copy the skill folder (.claude/skills/a11y-audit in plugin87/ux-ui-agent-skills) into .claude/skills/a11y-audit in your project. Claude Code loads it when a task matches its description.

How do I install Accessibility Audit in Codex?

Run `npx skills add plugin87/ux-ui-agent-skills --skill a11y-audit -a codex`. Or copy the skill folder (.claude/skills/a11y-audit in plugin87/ux-ui-agent-skills) into .agents/skills/a11y-audit in your project. Codex loads it when a task matches its description.

Can I use Accessibility Audit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add plugin87/ux-ui-agent-skills --skill a11y-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/a11y-audit, .gemini/skills/a11y-audit, .github/skills/a11y-audit and .opencode/skills/a11y-audit in your project.

What does Accessibility Audit need to run?

Going by SKILL.md and its folder, Accessibility Audit needs the command-line tools its instructions call (npx, node and python3). Our summary lists: The ux-ui-agent-skills kit installed, not only the skill folders; Node.js and Python 3 to run the contrast and render scripts.

Does Accessibility Audit access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Accessibility Audit safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Accessibility Audit use?

Accessibility Audit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Accessibility Audit use?

About 542 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Accessibility Audit?

Skills that share tags, products or a category with Accessibility Audit: Web Interface Guidelines Reviewer (vercel-labs/openreview, 1.7k stars), Accessibility Review (markmead/hyperui, 12k stars), Web Animation Design (baptisteArno/typebot.io, 11k stars) and Accessibility Fixer (ibelick/ui-skills, 9.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Accessibility Audit?

plugin87 (a GitHub user) maintains it in plugin87/ux-ui-agent-skills, which has 1,543 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 7, 2026.

Source: plugin87/ux-ui-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.