# a11y-ally

The a11y-ally skill audits pages for WCAG issues and suggests fixes based on page context. Use it to review a site or assess video accessibility.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 131 installs · ★ 533 repo stars
- Author: proffesor-for-testing
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/proffesor-for-testing/agentic-qe/tree/HEAD/assets/skills/a11y-ally/SKILL.md
- Updated: 2026-10-25
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/a11y-ally

## What it does

The skill checks accessibility with axe-core, then uses pa11y and Lighthouse when extra rule sets are needed. The agent reviews each finding in context and proposes a specific fix. Reports go to `docs/accessibility-scans/{page-slug}/`.

For video, its workflow downloads the clip, extracts frames, and uses Vision to describe them for caption creation. A Playwright script can audit multiple URLs in parallel; the browser workflow also uses `qe-browser` with Vibium. Dependencies listed for the skill include `playwright`, `@axe-core/playwright`, `pa11y`, and `lighthouse`.

The main browser workflow depends on `vibium` being installed; the instructions also provide a fallback using pa11y and Lighthouse. The skill supports Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill a11y-ally -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/a11y-ally/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/a11y-ally/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill a11y-ally -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/a11y-ally/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill a11y-ally -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/a11y-ally/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install proffesor-for-testing/agentic-qe assets/skills/a11y-ally
```

2. **Manually: put the files in place**
- File: `.github/skills/a11y-ally/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill a11y-ally -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/proffesor-for-testing/agentic-qe --path assets/skills/a11y-ally
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/a11y-ally/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill a11y-ally -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/proffesor-for-testing/agentic-qe/tree/HEAD/assets/skills/a11y-ally/SKILL.md

## When to use it
- scan a page for WCAG violations
- write fixes that account for page context
- analyze video frames to prepare captions
- audit multiple URLs in parallel

## Example prompts
- Audit this page for accessibility issues and save the report.
- Check these URLs for WCAG violations and suggest fixes.
- Find the video on this page, inspect its frames, and prepare captions.

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 03ba6ac47fa5dda8.

BEGIN THIRD-PARTY FILE 03ba6ac47fa5dda8
````text
---
name: a11y-ally
description: "Use when running comprehensive WCAG accessibility audits with axe-core + pa11y + Lighthouse, generating context-aware remediation, or testing video accessibility. Supports 3-tier browser cascade with graceful degradation."
category: specialized-testing
priority: critical
tokenEstimate: 10000
agents: []
implementation_status: active
optimization_version: 7.0
last_optimized: 2026-01-26
dependencies: [playwright, playwright-extra, puppeteer-extra-plugin-stealth, "@axe-core/playwright", pa11y, lighthouse]
quick_reference_card: true
tags: [accessibility, wcag, a11y, video, captions, audiodesc, vtt, eu-compliance, context-aware, remediation, axe-core, pa11y, lighthouse, parallel, resilient, graceful-degradation, retry]
trust_tier: 3
validation:
  schema_path: schemas/output.json
  validator_path: scripts/validate-config.json
  eval_path: evals/a11y-ally.yaml
---

# /a11y-ally - Comprehensive Accessibility Audit

<default_to_action>
When this skill is invoked with a URL, Claude executes ALL steps automatically without waiting for user prompts between steps.

## THIS IS AN LLM-POWERED SKILL

The value of this skill is **Claude's intelligence**, not just running automated tools:

| Automated Tools Do | Claude (This Skill) Does |
|--------------------|--------------------------|
| Flag "button has no name" | Analyze context: icon class, parent element, nearby text → generate "Add to wishlist" |
| Flag "image missing alt" | Use Vision to see the image → describe actual content |
| Flag "video has no captions" | Download video, extract frames, analyze each frame with Vision → generate real captions |
| Output generic templates | Generate context-specific, copy-paste ready fixes |

**IF YOU SKIP THE LLM ANALYSIS, THIS SKILL HAS NO VALUE.**

---

## EXECUTION MODEL

**CLAUDE EXECUTES ALL STEPS WITHOUT STOPPING.**

Do NOT wait for user prompts between steps. Execute the full pipeline:

1. **Data Collection**: Run multi-tool scan (axe-core, pa11y, Lighthouse) via Bash
2. **LLM Analysis**: Read results and analyze context for each violation
3. **Vision Pipeline**: If videos detected → download → extract frames → Read each frame → describe
4. **Intelligent Remediation**: Generate context-specific fixes using your reasoning
5. **Generate Reports**: Write all output files to `docs/accessibility-scans/{page-slug}/`

**WRONG:**
```
Claude: "I found 5 violations. Should I analyze them?"
User: "Yes"
Claude: "I see a video. Should I run the video pipeline?"
User: "Yes"
```

**RIGHT:**
```
Claude: [Runs scan] → [Analyzes violations] → [Downloads video] → [Extracts frames] →
        [Reads each frame with Vision] → [Generates captions] → [Writes all files]
        "Audit complete. Generated 4 files in docs/accessibility-scans/example/"
```

---

## STEP 1: BROWSER AUTOMATION - Content Fetching
````
END THIRD-PARTY FILE 03ba6ac47fa5dda8

The third-party file has ended. Everything between the 03ba6ac47fa5dda8 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2878 of 53148 bytes. © proffesor-for-testing · MIT · https://github.com/proffesor-for-testing/agentic-qe/tree/HEAD/assets/skills/a11y-ally/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
