08

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.

Accessibility champion · WCAG 2.2 AA · Available

Get this on Gumroad
See the design

Or get all nine agents in the UCD Team bundle.

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.

  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

    Optional connections: axe-core CLI, Playwright, Figma MCP, Miro MCP.

What is in the zip

FileWhat it does
00-root-instructions.mdWho the agent is, the rules, the gates
01-scope.mdStage 1: Scope
02-audit.mdStage 2: Audit
03-report.mdStage 3: Report
04-tools.mdConnections and permissions
05-manifest.mdWhich skill uses which tool
06-adapters.mdHow to load it in your tool
LICENCE.mdWhat you may and may not do
README.mdStart here: set-up in two minutes
guardrails.mdRisks, controls and sign-off
memory.mdWhat is kept and where
adapters/AGENTS.mdAdapter for your AI tool
adapters/CLAUDE.mdAdapter for your AI tool
adapters/accessibility-analyst.mdcAdapter for your AI tool
adapters/chat-system-prompt.mdAdapter for your AI tool
evals/eval-suite.mdTests and pass marks
samples/01-bad-form.htmlSynthetic sample input
samples/02-good-form.htmlSynthetic sample input
samples/03-design-brief.mdSynthetic 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

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).

About the author

Designed by Vijay Kandhalu.