WCAG 2.2 Accessibility Audit
AIPexStudio/AIPex
Audits a live webpage against eight core WCAG 2.2 success criteria, combining accessibility-tree inspection, visual screenshots and keyboard navigation tests, with evidence in the report.
How to test: screen readers, keyboard passes, automated checks and CI.
Install Testing Coach
$ npx skills add Community-Access/accessibility-agents --skill testing-coach -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Community-Access/accessibility-agents testing-coach --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Community-Access/accessibility-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/testing-coach .claude/skills/testing-coach && rm -rf skills-srcUse ~/.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/
Install the "testing-coach" agent skill from https://github.com/Community-Access/accessibility-agents/tree/main/skills/testing-coach into .claude/skills/testing-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "testing-coach", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Community-Access/accessibility-agents/tree/main/skills/testing-coachType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Community-Access/accessibility-agents --skill testing-coach -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Community-Access/accessibility-agents testing-coach --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Community-Access/accessibility-agents.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/testing-coach .agents/skills/testing-coach && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "testing-coach" agent skill from https://github.com/Community-Access/accessibility-agents/tree/main/skills/testing-coach into .agents/skills/testing-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "testing-coach", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Community-Access/accessibility-agents --skill testing-coach -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Community-Access/accessibility-agents testing-coach --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Community-Access/accessibility-agents.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/testing-coach .cursor/skills/testing-coach && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "testing-coach" agent skill from https://github.com/Community-Access/accessibility-agents/tree/main/skills/testing-coach into .cursor/skills/testing-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "testing-coach", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Community-Access/accessibility-agents.git --path skills/testing-coach--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Community-Access/accessibility-agents --skill testing-coach -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Community-Access/accessibility-agents testing-coach --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Community-Access/accessibility-agents.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/testing-coach .gemini/skills/testing-coach && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "testing-coach" agent skill from https://github.com/Community-Access/accessibility-agents/tree/main/skills/testing-coach into .gemini/skills/testing-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "testing-coach", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Community-Access/accessibility-agents testing-coachInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Community-Access/accessibility-agents --skill testing-coach -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Community-Access/accessibility-agents.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/testing-coach .github/skills/testing-coach && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "testing-coach" agent skill from https://github.com/Community-Access/accessibility-agents/tree/main/skills/testing-coach into .github/skills/testing-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "testing-coach", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Community-Access/accessibility-agents --skill testing-coach -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Community-Access/accessibility-agents testing-coach --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Community-Access/accessibility-agents.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/testing-coach .opencode/skills/testing-coach && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "testing-coach" agent skill from https://github.com/Community-Access/accessibility-agents/tree/main/skills/testing-coach into .opencode/skills/testing-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "testing-coach", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
testing-coach- GitHub stars
- 422
- Token cost
- ~1.5k tokens
- SKILL.md length
- 701 words
- Files
- 4 (incl. references)
- Skills in repo
- 108
- Repo updated
- First seen
- Licence
- MIT
At a glance
How to test: screen readers, keyboard passes, automated checks and CI.
- Works in 5 steps: Ask the user for their dev server URL… → Run: npx @axe-core/cli --tags… → Interpret the results: explain what each… → …
- Tasks that involve Accessibility
- SKILL.md covers Testing Coach, Your Scope, axe-core Integration and You Do NOT, plus 5 more sections
- Calls npx and npm
What it does
Testing Coach is an agent skill from Community-Access/accessibility-agents. How to test: screen readers, keyboard passes, automated checks and CI.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/automated-testing.md` and `references/screen-reader-testing.md`).
It sits in Frontend & Design, covering Accessibility. The repository describes itself as: Accessibility review agents for Claude Code, GitHub Copilot, and Claude Desktop. Eleven specialists that enforce WCAG 2.2 AA compliance so AI coding tools stop generating… The licence is MIT.
When your agent uses it
- Tasks that involve Accessibility
Example prompts
- “/testing-coach”
Requirements
- Node.js
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Ask the user for their dev server URL (e.g., http://localhost:3000)
- Run: npx @axe-core/cli --tags wcag2a,wcag2aa,wcag21a,wcag21aa
- Interpret the results: explain what each violation means in plain language
- Map violations to the appropriate specialist agent for fixes (contrast issues -> contrast-master, missing labels -> forms-specialist, etc.)
- Remind the user that automated scanning catches ~30% of issues - screen reader and keyboard testing are still required
What it can do on your machine
Read from SKILL.md and the folder at commit decf6ba. 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:
npxnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
w3.org
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
Testing Coach loads about 1.5k tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 21 tokens; SKILL.md has 701 words of instructions outside code blocks.
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 Community-Access/accessibility-agents at commit decf6ba, republished under its MIT licence (© Community-Access). 701 words, ~1,522 tokens.
Download SKILL.mdSave it as
.claude/skills/testing-coach/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- testing-coach
- description
- How to test: screen readers, keyboard passes, automated checks and CI.
- license
- MIT
- disable-model-invocation
- true
- metadata.tier
- specialist
- metadata.domain
- web
- metadata.output
- guidance
- metadata.effort
- medium
- metadata.title
- Testing Coach
Testing Coach
You are the accessibility testing coach. You do not write product code. You teach developers how to verify that their code actually works for people with disabilities. There is a massive gap between "the code looks right" and "it actually works in a screen reader." You bridge that gap.
Your Scope
You own everything related to accessibility testing methodology:
- Screen reader testing (NVDA, VoiceOver, JAWS, Narrator, TalkBack)
- Keyboard-only testing workflows
- Automated testing tools (axe-core, Pa11y, Lighthouse, WAVE)
- Browser DevTools accessibility features
- Testing frameworks integration (Playwright, Cypress, Jest)
- Accessibility test plans and checklists
- Manual testing procedures
- CI/CD accessibility testing pipelines
- Common testing mistakes and blind spots
axe-core Integration
You can run axe-core scans directly using the terminal. When the user has a running dev server:
- Ask the user for their dev server URL (e.g.,
http://localhost:3000) - Run:
npx @axe-core/cli <url> --tags wcag2a,wcag2aa,wcag21a,wcag21aa - Interpret the results: explain what each violation means in plain language
- Map violations to the appropriate specialist agent for fixes (contrast issues -> contrast-master, missing labels -> forms-specialist, etc.)
- Remind the user that automated scanning catches ~30% of issues - screen reader and keyboard testing are still required
If @axe-core/cli is not installed, tell the user to run: npm install -g @axe-core/cli
You can also help the user set up axe-core in their test framework (Playwright, Cypress, Jest) for ongoing automated checks in CI.
You Do NOT
- Write product feature code (that's the other specialists' job)
- Replace manual testing with automation (automation catches ~30% of issues)
- Guarantee compliance (testing reveals issues, it doesn't prove absence)
Keyboard Testing
This does NOT require a screen reader. Test keyboard access independently.
The 5-Minute Keyboard Test
- Unplug your mouse (or don't touch it)
- Press Tab - Can you see where focus is? If not, the focus indicator is missing or insufficient
- Tab through the entire page - Can you reach every interactive element?
- Press Enter/Space on every button and link - Do they work?
- Press Escape on any overlay - Does it close?
- Press Tab after closing an overlay - Does focus return to the trigger?
What Each Key Should Do
Each key, with its expected behavior.
| Key | Expected Behavior |
|---|---|
| Tab | Move to next interactive element |
| Shift+Tab | Move to previous interactive element |
| Enter | Activate link or button |
| Space | Activate button, toggle checkbox, open select |
| Escape | Close modal/dropdown/popover |
| Arrow keys | Navigate within a widget (tabs, radio group, menu, grid) |
| Home/End | Jump to first/last item in a list or menu |
Show full SKILL.md (292 more words)Show less
Keyboard Traps
A keyboard trap occurs when Tab gets stuck in a loop or a section with no exit. The only acceptable keyboard trap is inside a modal dialog (which must have Escape to exit).
Test for traps:
- Tab into every component
- Verify you can Tab out of it
- Pay special attention to: iframes, embedded widgets, custom dropdown menus, date pickers, rich text editors
Custom Widget Keyboard Patterns
When testing custom widgets, verify they follow the WAI-ARIA Authoring Practices:
| Widget | Expected Keyboard |
|---|---|
| Tabs | Arrow keys switch tabs, Tab moves to tab panel |
| Accordion | Enter/Space toggles, Arrow keys navigate headers |
| Menu | Arrow keys navigate, Enter selects, Escape closes |
| Dialog | Tab trapped inside, Escape closes, focus returns |
| Combobox | Arrow keys navigate options, Enter selects, Escape closes |
| Tree view | Arrow keys navigate, Enter expands/collapses |
| Slider | Arrow keys adjust value, Home/End for min/max |
Recommended Testing Combinations
These represent the majority of real-world assistive technology usage:
| Screen Reader | Browser | OS | Market Share |
|---|---|---|---|
| NVDA | Firefox | Windows | ~30% |
| NVDA | Chrome | Windows | ~20% |
| JAWS | Chrome | Windows | ~20% |
| VoiceOver | Safari | macOS | ~10% |
| VoiceOver | Safari | iOS | ~15% |
| TalkBack | Chrome | Android | ~5% |
Minimum viable testing: NVDA + Firefox, VoiceOver + Safari. This covers ~55% of assistive technology users and the two most different screen reader engines.
How to Report Testing Findings
For each issue found during testing:
### Issue: [Brief description]
- **Severity:** Critical / Major / Minor
- **Found by:** [Screen reader name] / Keyboard / Automated (axe-core)
- **Browser:** [Browser + version]
- **Steps to reproduce:**
1. Navigate to [page/component]
2. [Do specific action]
3. [Observe the problem]
- **Expected:** [What should happen]
- **Actual:** [What actually happens]
- **Screen reader announcement:** "[exact text announced]" (if applicable)
- **WCAG criterion:** [e.g., 1.1.1 Non-text Content, Level A]
- **Recommended fix:** [Brief description of how to fix]Reference files
Read one only when the task reaches it. Do not read them all up front.
references/screen-reader-testing.md- Screen Reader Testingreferences/automated-testing.md- Automated Testing, Browser DevTools Accessibility Features, Writing Accessibility Test Plans
Output contract
Answer the question. Keep the answer to what was asked, cite the criterion or API by name, and stop. Do not append a checklist that was not requested.
Shared rules, dispatch contract and schemas: skills/a11y-core/SKILL.md.
Authoritative specifications for this skill: skills/a11y-core/references/sources.md.
© Community-Access, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (references) in skills/testing-coach of Community-Access/accessibility-agents.
- SKILL.md
- agents/openai.yaml
- references/automated-testing.md
- references/screen-reader-testing.md
Open the folder on GitHubat commit decf6ba
Compare with similar skills
Testing Coach 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Testing Coach this skillCommunity-Access/accessibility-agents | 422 | — | ~1.5k | Automated safety check: Pass | MIT | |
| WCAG 2.2 Accessibility AuditAIPexStudio/AIPex | 1.3k | — | ~4.7k | Automated safety check: Pass | MIT | |
| Vrtmarigold-ui/marigold | 146 | — | ~787 | Automated safety check: Pass | MIT | |
| Scout UI Testingelastic/kibana | 21k | — | ~3.1k | Automated safety check: Pass | Custom licence | |
| Control UIcursor/plugins | 10k | 2 repos | ~1.2k | Automated safety check: Pass | None | |
| Accessibility Testingpetrkindlmann/qa-skills | 165 | — | ~4.5k | Automated safety check: Pass | MIT |
Similar skills
Vrt
marigold-ui/marigold
DST — Trigger the Visual-Regression-Tests (Chromatic) GitHub Actions workflow on the current or a given branch.
- Official
Scout UI Testing
elastic/kibana
A skill your agent uses when creating, updating, debugging, or reviewing Scout UI tests in Kibana (Playwright + Scout fixtures), including page objects, browser authentication, parallel UI tests…
- Official
Control UI
cursor/plugins
Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI.
Accessibility Testing
petrkindlmann/qa-skills
Test for WCAG 2.2 AA compliance with axe-core + Playwright, keyboard navigation audits, screen reader testing, ARIA pattern validation, and legal compliance mapping (ADA, EAA, Section 508).
Accessibility Testing
naodeng/awesome-qa-skills
A skill your agent uses when you need to design accessibility testing against WCAG, keyboard navigation, and assistive technology scenarios; triggers include accessibility testing and a11y testing.
More from Community-Access/accessibility-agents
All 108 skills in this repoA11y Core
Community-Access/accessibility-agents
Shared contract for the Accessibility Agents skills - dispatch, findings schema, report rules.
Kb Web Scanning
Community-Access/accessibility-agents
Reference data, not a reviewer. An agent skill from Community-Access/accessibility-agents.
Accessibility Lead
Community-Access/accessibility-agents
Web UI accessibility lead. An agent skill from Community-Access/accessibility-agents.
Alt Text Headings
Community-Access/accessibility-agents
Alt text, SVGs, figures, charts, heading order, page titles and landmarks.
Aria Specialist
Community-Access/accessibility-agents
ARIA roles, states and properties for custom widgets and dynamic content.
Cognitive Accessibility
Community-Access/accessibility-agents
Plain language, WCAG 2.2 cognitive criteria, COGA guidance and auth UX.
Related
Categories
Questions about Testing Coach
What does Testing Coach do?
How to test: screen readers, keyboard passes, automated checks and CI. Testing Coach is an agent skill from Community-Access/accessibility-agents. How to test: screen readers, keyboard passes, automated checks and CI.
When should I use Testing Coach?
Testing Coach fits situations like: tasks that involve Accessibility.
How do I install Testing Coach in Claude Code?
Run `npx skills add Community-Access/accessibility-agents --skill testing-coach -a claude-code`. Or copy the skill folder (skills/testing-coach in Community-Access/accessibility-agents) into .claude/skills/testing-coach in your project. Claude Code loads it when a task matches its description.
How do I install Testing Coach in Codex?
Run `npx skills add Community-Access/accessibility-agents --skill testing-coach -a codex`. Or copy the skill folder (skills/testing-coach in Community-Access/accessibility-agents) into .agents/skills/testing-coach in your project. Codex loads it when a task matches its description.
Can I use Testing Coach 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 Community-Access/accessibility-agents --skill testing-coach -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/testing-coach, .gemini/skills/testing-coach, .github/skills/testing-coach and .opencode/skills/testing-coach in your project.
What does Testing Coach need to run?
Going by SKILL.md and its folder, Testing Coach needs the command-line tools its instructions call (npx and npm). Our summary lists: Node.js.
Does Testing Coach access the network?
SKILL.md names 1 domain. As links in the text: w3.org. This is read from the text; nothing was executed.
Is Testing Coach 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 Testing Coach use?
Testing Coach is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Testing Coach use?
About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.9k tokens, read only when the agent opens those files.
What are the alternatives to Testing Coach?
Skills that share tags, products or a category with Testing Coach: WCAG 2.2 Accessibility Audit (AIPexStudio/AIPex, 1.3k stars), Vrt (marigold-ui/marigold, 146 stars), Scout UI Testing (elastic/kibana, 21k stars) and Control UI (cursor/plugins, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Testing Coach?
Community-Access (a GitHub organization) maintains it in Community-Access/accessibility-agents, which has 422 GitHub stars. The repository holds 108 skills in this directory. The repository was last updated on September 23, 2026.
Source: Community-Access/accessibility-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.