Accessibility Auditor logo

Accessibility Auditor

Organization
TerminalSkills
accessibility-auditor

Audit web pages and components for WCAG 2.2 accessibility compliance. Use when a user asks to check accessibility, find a11y issues, audit for WCAG compliance, fix screen reader problems, check color contrast, ensure keyboard navigation works, or prepare for accessibility regulations like the European Accessibility Act or ADA.

Overview

PublisherTerminalSkills
Repositoryskills
Skill nameaccessibility-auditor
Stars
155
Forks
21
Bundled files
1
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by TerminalSkills on GitHub. Read the source before you install it.

Installation

Install the Accessibility Auditor AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/TerminalSkills/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/accessibility-auditor .claude/skills/accessibility-auditor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Accessibility Auditor in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Accessibility Auditor on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Accessibility Auditor is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Accessibility Auditor

Overview

Audits web pages and UI components against WCAG 2.2 (Level AA) success criteria. Identifies violations in color contrast, keyboard navigation, ARIA usage, semantic HTML, form labeling, focus management, and dynamic content updates. Produces actionable fixes with exact code changes.

Instructions

When asked to audit accessibility:

  1. Determine the scope:

    • Single component, full page, or entire application?
    • Target compliance level: A, AA (default), or AAA?
    • Any specific regulations: EAA (European Accessibility Act), ADA, Section 508?
  2. Check semantic structure (WCAG 1.3.1, 1.3.2):

    • Heading hierarchy: h1 → h2 → h3, no skipped levels
    • Landmark regions: <nav>, <main>, <header>, <footer>, <aside>
    • Lists use <ul>/<ol>/<dl>, not styled <div>s
    • Tables have <th> with scope, and <caption> where appropriate
    • Reading order matches visual order
  3. Check text alternatives (WCAG 1.1.1):

    • All <img> have meaningful alt text (not "image", "photo", or filename)
    • Decorative images use alt="" or role="presentation"
    • SVG icons have <title> or aria-label
    • Complex images (charts, diagrams) have extended descriptions
    • Video/audio have captions and transcripts
  4. Check color and contrast (WCAG 1.4.3, 1.4.11):

    • Normal text: minimum 4.5:1 contrast ratio
    • Large text (18px+ or 14px+ bold): minimum 3:1
    • UI components and graphical objects: minimum 3:1
    • Information not conveyed by color alone (WCAG 1.4.1)
    • Compute exact contrast ratios for flagged elements
  5. Check keyboard accessibility (WCAG 2.1.1, 2.1.2, 2.4.7):

    • All interactive elements reachable via Tab key
    • No keyboard traps (user can always Tab away)
    • Focus indicators visible (not outline: none without replacement)
    • Custom components have appropriate keyboard handlers (Enter, Space, Arrow keys)
    • Modal dialogs trap and restore focus correctly
    • Skip-to-content link present
  6. Check ARIA usage (WCAG 4.1.2):

    • ARIA roles match element behavior
    • Required ARIA attributes present (e.g., aria-expanded on toggles)
    • aria-live regions for dynamic content updates
    • No redundant ARIA (e.g., role="button" on <button>)
    • aria-label/aria-labelledby on elements without visible text
  7. Check forms (WCAG 1.3.5, 3.3.1, 3.3.2):

    • All inputs have associated <label> elements (not just placeholder text)
    • Error messages are programmatically associated with inputs
    • Required fields indicated with more than just color
    • autocomplete attributes on common fields (name, email, address)
    • Form validation errors announced to screen readers
  8. Output format for each violation:

    • WCAG criterion number and name
    • Severity: Critical / Major / Minor
    • Element and location (file:line or CSS selector)
    • What's wrong (specific, not generic)
    • Exact code fix
    • Who is affected (screen reader users, keyboard users, low vision, etc.)

Examples

Example 1: Component audit

Input:

Audit this React login form for accessibility:
<form onSubmit={handleLogin}>
  <input type="email" placeholder="Email" value={email} onChange={setEmail} />
  <input type="password" placeholder="Password" value={pw} onChange={setPw} />
  <div className="error" style={{color: 'red'}}>{error}</div>
  <div className="submit-btn" onClick={handleLogin}>Log In</div>
</form>

Output:

Accessibility Audit: Login Form
=================================
6 violations found (3 Critical, 2 Major, 1 Minor)

CRITICAL [WCAG 1.3.5] — Missing autocomplete attributes
  Elements: email input, password input
  Fix: Add autocomplete="email" and autocomplete="current-password"
  Affected: Users relying on autofill, password managers, and assistive tech

CRITICAL [WCAG 3.3.2] — Inputs have no accessible labels
  Elements: both <input> fields
  Problem: Placeholder text disappears on focus and is not a label.
  Fix: Add <label htmlFor="email">Email</label> before each input,
       or use aria-label="Email address" as minimum.

CRITICAL [WCAG 2.1.1] — Submit button is not keyboard accessible
  Element: <div className="submit-btn">
  Problem: <div> is not focusable and onClick doesn't fire on Enter key.
  Fix: Replace with <button type="submit">Log In</button>

MAJOR [WCAG 3.3.1] — Error message not associated with input
  Element: <div className="error">
  Fix: Add role="alert" and aria-live="polite" to announce errors.
       Associate with input: aria-describedby="login-error" on the relevant input.

MAJOR [WCAG 1.4.1] — Error indicated by color alone
  Element: error div with color: red
  Fix: Add an icon (⚠) or prefix "Error:" to the text.

MINOR [WCAG 1.4.3] — Verify error text contrast
  Red (#FF0000) on white (#FFFFFF) = 4.0:1 — fails for normal text.
  Fix: Use #D32F2F (darker red) for 5.9:1 ratio.

Example 2: Keyboard navigation audit

Input:

Check keyboard accessibility of our dropdown menu component in src/components/Dropdown.tsx

Output:

Keyboard Audit: Dropdown Component
====================================
3 violations found.

CRITICAL [WCAG 2.1.2] — Keyboard trap in open dropdown
  When dropdown is open, Tab moves focus into the list but pressing Escape
  does nothing. User is trapped.
  Fix: Add onKeyDown handler:
    if (e.key === 'Escape') { setOpen(false); triggerRef.current.focus(); }

MAJOR [WCAG 2.1.1] — Arrow key navigation missing
  Dropdown items are only reachable via Tab. Standard pattern requires
  ArrowDown/ArrowUp to move between options.
  Fix: Add roving tabIndex pattern — active item gets tabIndex={0},
       others get tabIndex={-1}. ArrowDown moves focus to next item.

MAJOR [WCAG 4.1.2] — Missing ARIA attributes
  The trigger button lacks aria-expanded and aria-haspopup.
  Fix: <button aria-expanded={isOpen} aria-haspopup="listbox">
       The list needs role="listbox" and items need role="option".

Guidelines

  • Default to WCAG 2.2 Level AA unless the user specifies otherwise.
  • Always provide exact code fixes, not just descriptions of the problem.
  • Prioritize Critical issues (blocks entire user groups) over Minor (suboptimal experience).
  • Test ARIA patterns against established WAI-ARIA Authoring Practices for correctness.
  • Note that automated audits catch ~30% of accessibility issues — recommend manual testing with screen readers for the rest.
  • For color contrast, calculate actual ratios — don't eyeball it.
  • Flag tabIndex values greater than 0 as an anti-pattern (disrupts natural tab order).

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Accessibility Auditor AI skill do?

Audit web pages and components for WCAG 2.2 accessibility compliance. Use when a user asks to check accessibility, find a11y issues, audit for WCAG compliance, fix screen reader problems, check color contrast, ensure keyboard navigation works, or prepare for accessibility regulations like the European Accessibility Act or ADA.

Why use Accessibility Auditor on TypingMind?

Because you install it once and use it with any model. Accessibility Auditor is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Accessibility Auditor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/TerminalSkills/skills/tree/main/skills/accessibility-auditor. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Accessibility Auditor?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Accessibility Auditor?

As many as you like. As long as a model supports skills, you can use Accessibility Auditor with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Accessibility Auditor AI skill free?

Yes. It is published on GitHub by TerminalSkills under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇