# Accessibility Analyst

## Is your service usable by everyone, equally? Find out before you ship.

Accessibility Analyst audits pages and designs against WCAG 2.2 AA, names the fix for every issue, ranks fixes by user impact, and tells you plainly what risk remains.

[Get this on Gumroad](https://2111537314989.gumroad.com/l/accessibility-analyst) · [See the design](./anatomy)

## The problem
- Accessibility gets checked at the end, when fixes are expensive.
- Audit reports say what failed but not how to fix it.
- Automated tools give false confidence.

## What it does
- Runs automated WCAG 2.2 AA checks on built pages
- Reviews designs for contrast, focus order, labels and target size
- Simulates a screen reader walk-through of your main journey
- Lists the 2.2 criteria a person must still check
- Ranks fixes by user impact and effort, with a plain-English risk summary

## How it works
1. Get this on Gumroad and download the zip.
2. Unzip it into a project folder and open it in your AI tool.
3. Say `audit <URL, folder or design> for accessibility`.
4. It works one stage at a time and stops for your yes.

| Stage | You get, then approve |
|---|---|
| 1. Scope | Audit scope |
| 2. Audit | Automated audit, Design review, Screen reader walk-through (simulated), Manual checklist |
| 3. Report | Remediation ranking, Residual risk, Design annotations |

## Built to a standard
WCAG 2.2 AA. Every claim cites its source. Nothing is written to your tools without your approval.

## Who it is for
Delivery managers, product owners and engineers who are not accessibility specialists but need audit-ready findings.

## What you need
- An AI tool that reads project instructions: Claude Code, Cursor, or a tool that reads AGENTS.md. Claude Projects and custom bots work too, with copy-and-paste outputs.
- Your own AI subscription or API key. Nothing to host.
- Optional connections: axe-core CLI, Playwright, Figma MCP, Miro MCP.

## What is in the zip
| File | What it does |
|---|---|
| `00-root-instructions.md` | Who the agent is, the rules, the gates |
| `01-scope.md` | Stage 1: Scope |
| `02-audit.md` | Stage 2: Audit |
| `03-report.md` | Stage 3: Report |
| `04-tools.md` | Connections and permissions |
| `05-manifest.md` | Which skill uses which tool |
| `06-adapters.md` | How to load it in your tool |
| `LICENCE.md` | What you may and may not do |
| `README.md` | Start here: set-up in two minutes |
| `guardrails.md` | Risks, controls and sign-off |
| `memory.md` | What is kept and where |
| `adapters/AGENTS.md` | Adapter for your AI tool |
| `adapters/CLAUDE.md` | Adapter for your AI tool |
| `adapters/accessibility-analyst.mdc` | Adapter for your AI tool |
| `adapters/chat-system-prompt.md` | Adapter for your AI tool |
| `evals/eval-suite.md` | Tests and pass marks |
| `samples/01-bad-form.html` | Synthetic sample input |
| `samples/02-good-form.html` | Synthetic sample input |
| `samples/03-design-brief.md` | Synthetic sample input |

## Questions
**Is this a formal audit?**
No. It is a first pass that makes a formal audit faster and cheaper. It never claims compliance.

**Does it need anything installed?**
Node.js for the automated checks. Design review works from Figma or screenshots.

**Does it test with disabled users?**
No. Nothing replaces that. The report tells you what to test.

**Can I change the files?**
Yes. They are plain markdown. The licence lets you adapt them for your own work.

## Designed before it was built
This agent was designed with the five-question method: purpose, boundaries, what it touches, when a person steps in, and how you know it works. [Read the design](./anatomy).

[Get this on Gumroad](https://2111537314989.gumroad.com/l/accessibility-analyst)