Accessibility Audit logo

Accessibility Audit

Community
RealTask
accessibility-audit

Audit and improve interface accessibility across semantics, keyboard use, focus, forms, contrast, zoom, touch, and reduced-motion behavior.

Overview

PublisherRealTask
RepositoryMAX-DESIGN
Skill nameaccessibility-audit
Stars
4
Forks
0
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Accessibility Audit 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.
    https://github.com/RealTask/MAX-DESIGN/tree/main/skills/accessibility-audit
  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/RealTask/MAX-DESIGN.git /tmp/MAX-DESIGN
mkdir -p .claude/skills
cp -r /tmp/MAX-DESIGN/skills/accessibility-audit .claude/skills/accessibility-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Accessibility Audit 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 Audit 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 Audit 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 audit

When to use

Use before shipping UI, when building custom controls, reviewing forms or navigation, working from design screenshots, or changing focus, motion, contrast, or responsive access.

Workflow

1. Inspect the implementation

Review the actual DOM and source when available. Determine whether controls use native semantic elements, landmarks and headings communicate structure, and labels, descriptions, and validation are programmatically connected. A screenshot alone cannot establish semantic or screen-reader behavior.

2. Check keyboard operation

Navigate without a pointer. Confirm logical tab order, visible focus, working activation, escape behavior for dismissible overlays, and focus return after a dialog closes. Ensure users cannot become trapped unintentionally and sticky UI does not cover focused elements.

3. Check names, roles, and state

Interactive controls need accessible names and correct semantics. Prefer native buttons, links, inputs, selects, and checkboxes where possible. Custom widgets must implement expected keyboard patterns and expose state. Do not add ARIA roles that conflict with native semantics.

4. Check text and contrast

Review text resizing, wrapping, readable line lengths, color contrast, focus indicators, non-text boundaries, and status messages. Do not communicate meaning through color alone. Verify important combinations against applicable WCAG success criteria rather than judging by eye.

5. Check forms and feedback

Provide persistent labels, clear instructions, associated error messages, correction guidance, and appropriate announcements for asynchronous results. Errors should identify the affected field and explain how to resolve the issue. Do not erase user input unnecessarily after failure.

6. Check responsive and input modes

Test zoom and narrow layouts. Look for clipped content, unnecessary horizontal scrolling, overlapping controls, tiny or crowded targets, hover-only information, and gestures without alternatives. Ensure touch and pointer interaction do not block keyboard access.

7. Check motion and media

Respect reduced-motion preferences. Provide captions or text alternatives for meaningful media, and appropriate alternative text for informative images. Decorative images should not add redundant announcements. Avoid disruptive autoplay.

8. Verify with layered methods

Use automated checks for detectable problems, then manually inspect keyboard flow and semantics. Test with real assistive technology when the risk and environment justify it. Automated tools cannot prove conformance. Report tools, scope, conditions, and untested areas.

9. Prioritize fixes

Fix barriers that block core tasks first. Give each issue a location, evidence, impact, remediation, and verification method. Distinguish observed failures from risk hypotheses. Do not make blanket conformance claims without appropriate evaluation.

Quality gates

  • Semantic structure and accessible names are understandable.
  • All functionality is keyboard-operable and focus is visible.
  • Custom controls expose correct role, name, value, and state.
  • Text, controls, boundaries, and focus meet applicable contrast expectations.
  • Zoom, text wrapping, errors, and status feedback remain usable.
  • Color is not the sole source of meaning.
  • Reduced-motion settings and text alternatives are handled.
  • Test coverage, tools, and limitations are reported honestly.

Frequently asked questions

What does the Accessibility Audit AI skill do?

Audit and improve interface accessibility across semantics, keyboard use, focus, forms, contrast, zoom, touch, and reduced-motion behavior.

Why use Accessibility Audit on TypingMind?

Because you install it once and use it with any model. Accessibility Audit 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 Audit in TypingMind?

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

Which AI models can use Accessibility Audit?

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 Audit?

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

Is the Accessibility Audit AI skill free?

Yes. It is published on GitHub by RealTask under the MIT 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 👇