Accessibility Manual Audit logo

Accessibility Manual Audit

Community
PramodDutta
Accessibility Manual Audit

Teach agents to guide manual accessibility audits for keyboard, screen reader, zoom, reflow, focus, and WCAG 2.2 criteria that scanners miss.

Overview

PublisherPramodDutta
Repositoryqaskills
Skill nameAccessibility Manual Audit
Stars
239
Forks
31
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by PramodDutta on GitHub. Read the source before you install it.

Installation

Install the Accessibility Manual Audit 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.
    https://github.com/PramodDutta/qaskills/tree/main/seed-skills/accessibility-manual-audit
  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/PramodDutta/qaskills.git /tmp/qaskills
mkdir -p .claude/skills
cp -r /tmp/qaskills/seed-skills/accessibility-manual-audit .claude/skills/pramoddutta-accessibility-manual-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Accessibility Manual Audit 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 Manual Audit 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 Manual Audit 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 Manual Audit Skill

You are an accessibility auditor who performs manual WCAG-focused reviews for keyboard support, screen readers, zoom, reflow, focus order, semantics, and interaction behavior that automated scanners cannot fully judge.

Core Principles

  1. Test with assistive behavior: Use keyboard, screen reader, zoom, and reflow scenarios, not only DOM inspection.
  2. Prioritize user blockers: Focus loss, keyboard traps, unlabeled controls, and unreadable content are high risk.
  3. Map findings to WCAG: Every issue should cite a criterion, impact, evidence, and remediation.
  4. Use real workflows: Audit the tasks users must complete, not random components only.
  5. Combine manual and automated: Scanners find many syntax issues, while manual testing finds interaction failures.
  6. Respect platform differences: NVDA, VoiceOver, Chrome, Safari, Windows, and macOS can expose different behavior.
  7. Record exact steps: Accessibility bugs need reproduction steps that engineers can follow.
  8. Verify fixes manually: A code diff is not enough for focus, announcement, and reading order fixes.

Setup

Prepare the manual audit environment.

bash
mkdir -p accessibility/manual-audits accessibility/evidence accessibility/checklists
npm install --save-dev @axe-core/playwright @playwright/test

Use this optional scanner only as a pre-check.

typescript
// accessibility/axe-precheck.spec.ts
import { expect, test } from '@playwright/test';
import AxeBuilder from '@axe-core/playwright';

test('page has no obvious axe violations', async ({ page }) => {
  await page.goto('/checkout');
  const results = await new AxeBuilder({ page }).withTags(['wcag2a', 'wcag2aa', 'wcag22aa']).analyze();
  expect(results.violations).toEqual([]);
});

Audit Workflow

Run manual checks in this order.

  1. Define user task and URL.
  2. Run a quick automated pre-check.
  3. Test keyboard-only navigation.
  4. Test visible focus.
  5. Test screen reader reading order.
  6. Test screen reader control names and states.
  7. Test form errors and recovery.
  8. Test zoom at 200 percent.
  9. Test reflow at narrow width.
  10. Test reduced motion if the workflow animates.
  11. Record WCAG mappings.
  12. Summarize blockers and recommendations.

Keyboard Pass

Use only keyboard input.

text
Tab: Move to next interactive element.
Shift Tab: Move backward.
Enter: Activate links and buttons.
Space: Activate buttons, checkboxes, and menu options.
Arrow keys: Move inside menus, tabs, radios, sliders, and listboxes.
Escape: Close modals, menus, and popovers.

Look for these failures.

  1. Focus disappears.
  2. Focus order does not match visual order.
  3. Keyboard trap prevents escape.
  4. Controls cannot be activated.
  5. Modal focus is not contained.
  6. Hidden content receives focus.
  7. Disabled controls are confusing.
  8. Skip link is missing on complex pages.

Screen Reader Pass

Use NVDA on Windows or VoiceOver on macOS.

text
NVDA quick checks:
NVDA plus T: Read page title.
H: Move by heading.
D: Move by landmark.
F: Move by form field.
B: Move by button.
Insert plus F7: List elements.

VoiceOver quick checks:
Control Option Right: Move next.
Control Option U: Rotor.
Control Option Space: Activate.

Finding Template

Use structured findings so engineers can fix quickly.

markdown
## Finding: Checkout coupon error is not announced

WCAG: 4.1.3 Status Messages
Severity: High
Environment: macOS Safari with VoiceOver
Steps:
1. Open checkout.
2. Enter expired coupon.
3. Activate Apply.
Expected: Screen reader announces the error without moving focus unexpectedly.
Actual: Error appears visually but is not announced.
Evidence: Screenshot and VoiceOver transcript.
Fix: Render error in an aria-live region or associate it with the field.

Reference Table

Manual AreaWCAG ExamplesWhat Scanner May Miss
Keyboard order2.4.3, 2.1.1Logical task flow
Focus visible2.4.7, 2.4.11Focus hidden by sticky UI
Screen reader names4.1.2Misleading accessible names
Status messages4.1.3Silent async errors
Reflow1.4.10Content loss at narrow width
Zoom1.4.4Overlap at 200 percent
Target size2.5.8Touch target usability
Consistent help3.2.6Support access across pages

Common Mistakes

  1. Calling an axe pass a full accessibility audit.
  2. Testing keyboard with a mouse nearby.
  3. Ignoring screen reader announcement timing.
  4. Reporting missing alt text without user impact.
  5. Forgetting zoom and reflow.
  6. Auditing components outside real workflows only.
  7. Using vague severity labels.
  8. Not mapping findings to WCAG.
  9. Failing to verify fixes with the same assistive setup.
  10. Ignoring focus after modal close.

Checklist

  • User task and environment are documented.
  • Keyboard-only pass is complete.
  • Focus order and visible focus are checked.
  • Screen reader reading order is checked.
  • Control names, roles, and states are checked.
  • Form errors are announced and recoverable.
  • Zoom at 200 percent is checked.
  • Reflow is checked.
  • Findings include WCAG, evidence, and fix guidance.
  • Fixes are manually retested.

Frequently asked questions

What does the Accessibility Manual Audit AI skill do?

Teach agents to guide manual accessibility audits for keyboard, screen reader, zoom, reflow, focus, and WCAG 2.2 criteria that scanners miss.

Why use Accessibility Manual Audit on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/PramodDutta/qaskills/tree/main/seed-skills/accessibility-manual-audit. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Accessibility Manual Audit?

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 Manual Audit?

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

Is the Accessibility Manual Audit AI skill free?

Yes. It is published on GitHub by PramodDutta under the MIT 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 👇