Qe Visual Accessibility logo

Qe Visual Accessibility

Community
proffesor-for-testing
qe-visual-accessibility

Captures and compares screenshots across viewports, runs axe-core accessibility scans, and detects visual regressions with pixel-diff analysis. Use when detecting UI regressions, validating responsive layouts, testing WCAG compliance, or ensuring visual consistency after CSS or component changes.

Overview

Publisherproffesor-for-testing
Repositoryagentic-qe
Skill nameqe-visual-accessibility
Stars
480
Forks
92
Bundled files
3
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.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by proffesor-for-testing on GitHub. Read the source before you install it.

Installation

Install the Qe Visual Accessibility 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.
  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/proffesor-for-testing/agentic-qe.git /tmp/agentic-qe
mkdir -p .claude/skills
cp -r /tmp/agentic-qe/assets/skills/qe-visual-accessibility .claude/skills/qe-visual-accessibility
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Qe Visual Accessibility 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 Qe Visual Accessibility 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 Qe Visual Accessibility 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.

QE Visual Accessibility

Purpose

Guide the use of v3's visual and accessibility testing capabilities including screenshot comparison, responsive design validation, and WCAG 2.2 compliance verification.

Activation

  • When testing visual appearance
  • When validating responsive design
  • When checking accessibility compliance
  • When detecting visual regressions
  • When testing cross-browser rendering

Quick Start

bash
# Visual regression test
aqe visual test --baseline production --current staging

# Responsive design test
aqe visual responsive --url https://example.com --viewports all

# Accessibility audit
aqe a11y audit --url https://example.com --standard wcag22-aa

# Cross-browser test
aqe visual cross-browser --url https://example.com --browsers chrome,firefox,safari

Agent Workflow

typescript
// Visual regression testing
Task("Run visual regression", `
  Compare staging against production:
  - Capture screenshots of key pages
  - Detect pixel differences
  - Flag significant visual changes
  - Generate visual diff report
`, "qe-visual-tester")

// Accessibility audit
Task("Audit accessibility", `
  Run WCAG 2.2 AA compliance audit:
  - Check color contrast ratios
  - Verify keyboard navigation
  - Test screen reader compatibility
  - Validate ARIA labels
  Generate compliance report with fix suggestions.
`, "qe-accessibility-agent")

Browser engine

All browser automation in this skill uses the qe-browser fleet skill (Vibium engine). See .claude/skills/qe-browser/SKILL.md. The vibium binary is installed by aqe init.

Visual Testing Operations

1. Visual Regression (via qe-browser)

bash
# Establish baselines for the pages we care about
for path in / /login /dashboard /settings; do
  slug=$(echo "$path" | tr '/' '_' | sed 's/^_//' || echo root)
  vibium go "https://production.example.com$path" && vibium wait load
  node .claude/skills/qe-browser/scripts/visual-diff.js --name "baseline_${slug:-root}"
done

# Compare staging against those baselines
for path in / /login /dashboard /settings; do
  slug=$(echo "$path" | tr '/' '_' | sed 's/^_//' || echo root)
  vibium go "https://staging.example.com$path" && vibium wait load
  node .claude/skills/qe-browser/scripts/visual-diff.js \
    --name "baseline_${slug:-root}" --threshold 0.001  # 0.1% pixel diff
done

Ignore dynamic regions (timestamps, live counts) by scoping the diff to a selector that excludes them:

bash
node .claude/skills/qe-browser/scripts/visual-diff.js \
  --name hero --selector "main > .content"

Legacy programmatic TypeScript API (still available for tests that prefer it over shelling out):

typescript
await visualTester.compareScreenshots({
  baseline: {
    source: 'production',
    pages: ['/', '/login', '/dashboard', '/settings']
  },
  current: {
    source: 'staging',
    pages: ['/', '/login', '/dashboard', '/settings']
  },
  comparison: {
    threshold: 0.1,  // 0.1% pixel difference
    antialiasing: true,
    ignoreRegions: ['#dynamic-content', '.timestamp']
  }
});

2. Responsive Testing

typescript
await responsiveTester.test({
  url: 'https://example.com',
  viewports: [
    { name: 'mobile', width: 375, height: 667 },
    { name: 'tablet', width: 768, height: 1024 },
    { name: 'desktop', width: 1920, height: 1080 }
  ],
  checks: {
    layoutShift: true,
    contentOverflow: true,
    touchTargets: true,
    fontScaling: true
  }
});

3. Accessibility Audit

typescript
await accessibilityAgent.audit({
  url: 'https://example.com',
  standard: 'WCAG22-AA',
  checks: {
    perceivable: {
      colorContrast: true,
      textAlternatives: true,
      captions: true
    },
    operable: {
      keyboardAccessible: true,
      noTimingIssues: true,
      navigable: true
    },
    understandable: {
      readable: true,
      predictable: true,
      inputAssistance: true
    },
    robust: {
      compatible: true,
      parseErrors: true
    }
  }
});

4. Cross-Browser Testing

typescript
await visualTester.crossBrowser({
  url: 'https://example.com',
  browsers: ['chrome', 'firefox', 'safari', 'edge'],
  versions: 'latest-2',
  comparisons: {
    betweenBrowsers: true,
    betweenVersions: true,
    againstBaseline: true
  }
});

WCAG 2.2 Checklist

LevelCriteriaAuto-Testable
ANon-text Content
AInfo and RelationshipsPartial
AColor Contrast (4.5:1)
AKeyboard Accessible
AFocus Visible
AAReflow
AAText Spacing
AAAEnhanced Contrast (7:1)

Visual Test Report

typescript
interface VisualReport {
  summary: {
    pagesCompared: number;
    differencesFound: number;
    passRate: number;
  };
  comparisons: {
    page: string;
    viewport: string;
    baseline: string;
    current: string;
    diff: string;
    diffPercentage: number;
    status: 'pass' | 'fail' | 'review';
  }[];
  accessibility: {
    violations: A11yViolation[];
    passes: number;
    incomplete: number;
    score: number;
  };
  responsive: {
    viewport: string;
    issues: ResponsiveIssue[];
  }[];
}

Accessibility Report

typescript
interface AccessibilityReport {
  summary: {
    score: number;
    violations: number;
    warnings: number;
    passes: number;
  };
  violations: {
    id: string;
    impact: 'critical' | 'serious' | 'moderate' | 'minor';
    description: string;
    wcag: string[];
    elements: {
      selector: string;
      html: string;
      issue: string;
      fix: string;
    }[];
  }[];
  compliance: {
    wcagLevel: 'A' | 'AA' | 'AAA';
    criteriasMet: number;
    criteriasTotal: number;
  };
}

CI/CD Integration

yaml
visual_testing:
  on_pr:
    - capture_screenshots
    - compare_to_baseline
    - run_a11y_audit

  thresholds:
    visual_diff: 0.1
    a11y_violations: 0

  artifacts:
    - screenshots/
    - diffs/
    - a11y-report.html

Coordination

Primary Agents: qe-visual-tester, qe-accessibility-agent, qe-responsive-tester Coordinator: qe-visual-coordinator Related Skills: qe-test-execution, qe-quality-assessment

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Qe Visual Accessibility AI skill do?

Captures and compares screenshots across viewports, runs axe-core accessibility scans, and detects visual regressions with pixel-diff analysis. Use when detecting UI regressions, validating responsive layouts, testing WCAG compliance, or ensuring visual consistency after CSS or component changes.

Why use Qe Visual Accessibility on TypingMind?

Because you install it once and use it with any model. Qe Visual Accessibility 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 Qe Visual Accessibility in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/proffesor-for-testing/agentic-qe/tree/main/assets/skills/qe-visual-accessibility. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Qe Visual Accessibility?

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 Qe Visual Accessibility?

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

Is the Qe Visual Accessibility AI skill free?

Yes. It is published on GitHub by proffesor-for-testing 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 👇