Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
proffesor-for-testing avatar

Compatibility Testing

proffesor-for-testing/agentic-qe

  • 621 installs
  • 433 repo stars
  • Updated August 4, 2026
  • proffesor-for-testing/agentic-qe

compatibility-testing is an Agentic QE evaluation skill at version 1.0.0 that validates cross-browser, cross-platform, and cross-device consistency for developers shipping AI-generated interfaces before release.

About

compatibility-testing is version 1.0.0 of the Agentic QE Compatibility Testing Skill Evaluation Suite from proffesor-for-testing/agentic-qe. The skill provides a comprehensive evaluation framework for cross-browser and cross-platform compatibility testing, covering browser matrix coverage, device tier validation, responsive breakpoints, and visual difference detection. Developers reach for compatibility-testing before release when AI-generated UI code must behave consistently across Chrome, Safari, Firefox, mobile viewports, and multiple AI model outputs. The suite includes multi-model configuration for evaluating compatibility test quality itself. It produces structured test evaluation results rather than writing Playwright scripts from scratch.

  • Evaluates cross-browser, cross-platform, and cross-device compatibility
  • Tests browser matrix coverage, responsive breakpoints, and visual difference detection
  • Validates performance against Claude 3.5 Sonnet and Claude 3 Haiku models
  • MCP integration with namespace skill-validation and outcome tracking
  • Shares learning across qe-learning-coordinator, qe-queen-coordinator, and qe-visual-tester agents

Compatibility Testing by the numbers

  • 621 all-time installs (skills.sh)
  • +4 installs in the week ending Aug 4, 2026 (Skillselion tracking)
  • Ranked #587 of 2,153 Testing & QA skills by installs in the Skillselion catalog
  • Security screen: MEDIUM risk (skills.sh audit)
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/proffesor-for-testing/agentic-qe --skill compatibility-testing

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs621
repo stars★ 433
Security audit2 / 3 scanners passed
Last updatedAugust 4, 2026
Repositoryproffesor-for-testing/agentic-qe ↗

How do you test cross-browser AI-generated UI code?

Automatically validate that their AI-generated code and interfaces work consistently across browsers, devices, and AI models before release.

Who is it for?

QA engineers and developers releasing AI-generated web interfaces who need structured cross-browser and cross-device validation before production.

Skip if: Backend-only API services with no UI layer or teams satisfied with a single-browser smoke test without matrix coverage.

When should I use this skill?

A developer asks to validate cross-browser compatibility, responsive breakpoints, device tiers, or visual differences before shipping AI-generated UI.

What you get

Compatibility evaluation results covering browser matrix, device tiers, responsive breakpoints, and detected visual differences.

  • Compatibility evaluation report with browser and device matrix results

By the numbers

  • Agentic QE Compatibility Testing Skill Evaluation Suite version 1.0.0
  • Covers 4 evaluation areas: browser matrix, device tiers, responsive breakpoints, visual differences

Files

SKILL.mdMarkdownGitHub ↗

Compatibility Testing

Browser engine

Browser-driven checks (viewport emulation, responsive validation, cross-browser screenshots) should go through the qe-browser fleet skill (.claude/skills/qe-browser/). Vibium is installed by aqe init. Quick reference:

# Viewport emulation per breakpoint
vibium viewport 375 667   # mobile
vibium viewport 768 1024  # tablet
vibium viewport 1920 1080 # desktop

# Full device emulation (user-agent, DPR, touch)
vibium emulate-device "iPhone 15"

# Visual diff per viewport
for vp in "375 667 mobile" "768 1024 tablet" "1920 1080 desktop"; do
  read w h name <<< "$vp"
  vibium viewport $w $h
  node .claude/skills/qe-browser/scripts/visual-diff.js --name "homepage-$name"
done

Cross-browser (Firefox/Safari) still requires Playwright or a cloud device farm today — Vibium's BiDi backend is Chrome-only at v26.3.x.

<default_to_action> When validating cross-browser/platform compatibility: 1. DEFINE browser matrix (cover 95%+ of users) 2. TEST responsive breakpoints (mobile, tablet, desktop) 3. RUN in parallel across browsers/devices 4. USE cloud services for device coverage (BrowserStack, Sauce Labs) 5. COMPARE visual screenshots across platforms

Quick Compatibility Checklist:

  • Chrome, Firefox, Safari, Edge (latest + N-1)
  • Mobile Safari (iOS), Mobile Chrome (Android)
  • Screen sizes: 320px, 768px, 1920px
  • Test on actual target devices for critical flows

Critical Success Factors:

  • Users access from 100+ browser/device combinations
  • Test where users are, not where you develop
  • Cloud testing reduces 10 hours to 15 minutes

</default_to_action>

Quick Reference Card

When to Use

  • Before release
  • After CSS/layout changes
  • Launching in new markets
  • Responsive design validation

---

Cross-Browser with Playwright

// playwright.config.ts
import { defineConfig, devices } from '@playwright/test';

export default defineConfig({
  projects: [
    { name: 'chromium', use: { ...devices['Desktop Chrome'] } },
    { name: 'firefox', use: { ...devices['Desktop Firefox'] } },
    { name: 'webkit', use: { ...devices['Desktop Safari'] } },
    { name: 'mobile-chrome', use: { ...devices['Pixel 5'] } },
    { name: 'mobile-safari', use: { ...devices['iPhone 12'] } }
  ]
});

// Run: npx playwright test --project=chromium --project=firefox

---

Cloud Testing Integration

// BrowserStack configuration
const capabilities = {
  'browserName': 'Chrome',
  'browser_version': '118.0',
  'os': 'Windows',
  'os_version': '11',
  'browserstack.user': process.env.BROWSERSTACK_USER,
  'browserstack.key': process.env.BROWSERSTACK_KEY
};

// Parallel execution across devices
const deviceMatrix = [
  { os: 'Windows', browser: 'Chrome' },
  { os: 'OS X', browser: 'Safari' },
  { os: 'Android', device: 'Samsung Galaxy S24' },
  { os: 'iOS', device: 'iPhone 15' }
];

---

Agent-Driven Compatibility Testing

// Cross-platform visual comparison
await Task("Compatibility Testing", {
  url: 'https://example.com',
  browsers: ['chrome', 'firefox', 'safari', 'edge'],
  devices: ['desktop', 'tablet', 'mobile'],
  platform: 'browserstack',
  parallel: true
}, "qe-visual-tester");

// Returns:
// {
//   combinations: 12,  // 4 browsers × 3 devices
//   passed: 11,
//   differences: [{ browser: 'safari', device: 'mobile', diff: 0.02 }]
// }

---

Agent Coordination Hints

Memory Namespace

aqe/compatibility-testing/
├── browser-matrix/*     - Browser/version configurations
├── device-matrix/*      - Device configurations
├── visual-diffs/*       - Cross-browser visual differences
└── reports/*            - Compatibility reports

Fleet Coordination

const compatFleet = await FleetManager.coordinate({
  strategy: 'compatibility-testing',
  agents: [
    'qe-visual-tester',       // Visual comparison
    'qe-test-executor',       // Cross-browser execution
    'qe-performance-tester'   // Performance by platform
  ],
  topology: 'parallel'
});

---

Related Skills

  • mobile-testing - Mobile-specific testing
  • visual-testing-advanced - Visual regression
  • accessibility-testing - Cross-platform a11y

---

Remember

Cover 95%+ of your user base. Use analytics to identify actual browser/device usage. Don't waste time on browsers nobody uses.

With Agents: Agents orchestrate parallel cross-browser testing across cloud platforms. qe-visual-tester catches visual inconsistencies across platforms automatically.

Related skills

mattpocockTddFollow test-driven development with a strict red-green-refactor loop when creating reliable features or fixing bugs.544k196kobraTest Driven DevelopmentEnforce writing failing tests before any production implementation code.181k264kmattpocockQaRun conversational QA sessions that turn user-reported bugs into well-written, domain-aware GitHub issues without manual ticket writing.179k196kmattpocockMigrate To ShoehornAutomatically update TypeScript test files that rely on unsafe `as` type assertions by replacing them with type-safe partial objects from @total-typescript/shoehorn.164k196kanthropicsWebapp TestingVerify frontend behavior, debug UI issues, capture screenshots, and inspect logs of a running local web application using Playwright.123k165kmicrosoftPlaywright CliRun browser automation, generate element snapshots, inspect DOM attributes, and execute Playwright tests from the terminal.102k12.3k

How it compares

Choose compatibility-testing over unit-test skills when the release gate is cross-browser UI consistency and visual diffs rather than isolated function correctness.

FAQ

What does compatibility-testing evaluate?

compatibility-testing is the Agentic QE evaluation suite at version 1.0.0 for cross-browser and cross-platform testing. The skill evaluates browser matrix coverage, device tier validation, responsive breakpoints, and visual difference detection before release.

Does compatibility-testing support multiple AI models?

compatibility-testing includes multi-model configuration in its evaluation suite, allowing validation of compatibility test quality across different AI model outputs. The skill targets AI-generated code and interface consistency before shipping.

Is Compatibility Testing safe to install?

skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

Testing & QAtestingintegrations
Browse by category
AI & AgentsFrontend & DesignBackend & DataDev ToolsAutomationTesting & ReviewSecurityMonitoring & CloudDocs & Planning
Design & frontend
Design systemsAnimation & motionAccessibility (a11y)CSS & TailwindUI designUXDesign to codeshadcn/uiLanding pagesBest design skills
Most searched skills
find-skillscavemanfrontend-designbrainstormingsystematic-debuggingstop-slopemil-design-engui-ux-pro-maxkarpathy-guidelinesweb-design-guidelinesreact-best-practicesgrill-meimprovemicrosoft-foundryagent-browser
Browse all listings
All agent skillsAll MCP serversAll marketplacesAll plugins

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.