Accessibility Review logo

Accessibility Review

Organization
Asymmetric-al
accessibility-review

Audit and fix accessibility in Core UI. Use when changing or reviewing buttons, links, forms, validation, dialogs, menus, tabs, tables, keyboard interactions, focus management, accessible names, announcements, contrast, touch targets, reduced motion, or WCAG/a11y behavior.

Overview

PublisherAsymmetric-al
Repositorycore
Skill nameaccessibility-review
Stars
383
Forks
7
Bundled files
1
LicenseAGPL-3.0
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 Asymmetric-al on GitHub. Read the source before you install it.

Installation

Install the Accessibility Review 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/Asymmetric-al/core.git /tmp/core
mkdir -p .claude/skills
cp -r /tmp/core/docs/ai/skills/accessibility-review .claude/skills/accessibility-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Accessibility Review 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 Review 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 Review 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 review

Apply a focused accessibility pass without replacing Core's component system or mistaking automated checks for conformance.

Authority and boundaries

  1. Read docs/ai/rules/frontend.md and docs/ai/rules/testing.md first.
  2. Reuse @asym/ui Base UI primitives for dialogs, menus, tabs, tooltips, comboboxes, and other behavior-heavy widgets. Do not build ARIA replicas of behavior that a shared primitive already implements.
  3. Prefer native HTML semantics before adding roles or ARIA. ARIA supplements semantics; it does not repair incorrect interaction behavior.
  4. Use docs/ai/skills/components-build/SKILL.md for component API work and docs/ai/skills/emil-design-engineering/touch-accessibility.md for Core's touch and keyboard conventions.
  5. Keep fixes scoped. Do not migrate UI libraries or refactor unrelated layout.

Workflow

  1. Map the states. Identify the interactive controls, reading order, keyboard path, loading/empty/error states, responsive variants, and any content revealed only by hover or pointer input.
  2. Check semantics and names. Verify landmarks, headings, lists, table headers, labels, accessible names, descriptions, values, and state attributes.
  3. Exercise interaction. Use Tab and Shift+Tab, Enter/Space, arrow keys where the widget pattern requires them, and Escape for dismissible overlays. Check visible focus, initial focus, focus containment, and focus restoration.
  4. Check feedback. Associate helper and error text with fields, announce material async status changes, and ensure color, toast, or hover is never the only carrier of essential information.
  5. Check perception. Inspect contrast, zoom/reflow, touch targets, alt text, captions where applicable, and reduced-motion behavior. Preserve Core's global reduced-motion baseline instead of redeclaring it in an app.
  6. Verify proportionately. Run the focused automated suite, then perform the manual checks automation cannot prove. If asked only to review, report exact file:line evidence and concrete fixes without editing source.

Core patterns

  • Give every interactive control an accessible name. Label icon-only buttons; keep decorative icons out of the accessibility tree.
  • Use real button, a, label, fieldset, legend, th, ul/ol, and heading elements when they express the behavior.
  • Connect field help and errors with stable IDs and aria-describedby; set aria-invalid only when the field is invalid.
  • Expose expanded, selected, checked, pressed, busy, and current state through the native element or the applicable ARIA state.
  • Keep DOM order aligned with visual and keyboard order. Never use positive tabIndex to repair a broken sequence.
  • Use Core's touch-target tokens and shared controls instead of shrinking the hit area to match the visible glyph.

Verification

bash
bun run test:a11y

For new or materially changed routes, update tests/e2e/accessibility.spec.ts. Use @axe-core/playwright for repeatable violations and Playwright role locators for behavior. An axe pass does not prove keyboard order, focus quality, usable labels, alt-text intent, or complete WCAG conformance, so keep the manual interaction pass.

Checklist

  • Native semantics or an established Base UI primitive owns behavior.
  • Names, descriptions, relationships, values, and states are exposed.
  • Keyboard operation, focus visibility, containment, and restoration work.
  • Forms expose instructions and errors without relying on color or toast.
  • Contrast, zoom/reflow, touch, media, and reduced motion were considered.
  • Relevant automated and manual checks ran; remaining limits are stated.
  • Findings cite exact files/lines, or fixes remain minimal and targeted.

Provenance

See references/upstream.md for the reviewed upstream source, license, Core adaptations, and refresh workflow.

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 Review AI skill do?

Audit and fix accessibility in Core UI. Use when changing or reviewing buttons, links, forms, validation, dialogs, menus, tabs, tables, keyboard interactions, focus management, accessible names, announcements, contrast, touch targets, reduced motion, or WCAG/a11y behavior.

Why use Accessibility Review on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Asymmetric-al/core/tree/develop/docs/ai/skills/accessibility-review. 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 Review?

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 Review?

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

Is the Accessibility Review AI skill free?

Yes. It is published on GitHub by Asymmetric-al under the AGPL-3.0 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 👇