Skip to content
Development
Skill

/browser-validator

Automatically validate implementations in real browsers after code is written or when user says "test this", "test what you built in the browser", "check it in a real browser", or "validate at the breakpoints". Uses Chrome DevTools MCP to test responsive breakpoints (320px,

From plugin
cms-cultivator
1728 skills1 agent

Claude Code

$ npx -y skills add kanopi/cms-cultivator --skill browser-validator --agent claude-code

SKILL.md

browser-validator.SKILL.md
name: browser-validator
description: Automatically validate implementations in real browsers after code is written or when user says "test this", "test what you built in the browser", "check it in a real browser", or "validate at the breakpoints". Uses Chrome DevTools MCP to test responsive breakpoints (320px, 768px, 1024px), check accessibility compliance (WCAG AA contrast, keyboard navigation, ARIA), validate interactions, and generate detailed technical reports with file paths and specific fixes.

Browser Validator Skill

Purpose

Validate design implementations in real browsers using Chrome DevTools MCP to ensure quality, accessibility, and responsiveness.

Philosophy

Real browser testing catches issues that code review cannot.

Core Beliefs

1. **Test in Real Environments**: Browsers behave differently than localhost 2. **Multiple Breakpoints Required**: Mobile, tablet, desktop have different challenges 3. **Accessibility Requires Manual Verification**: Automated tools miss context-dependent issues 4. **Visual QA Prevents Surprises**: Screenshots catch layout breaks before users see them

Why Browser Validation Matters

  • **Cross-Browser Consistency**: Ensure components work everywhere
  • **Responsive Behavior**: Verify breakpoints function correctly
  • **Accessibility Compliance**: Check keyboard navigation and screen reader compatibility
  • **Professional Quality**: Catch visual regressions before deployment

When This Skill Activates

This skill automatically activates when:

  • User says "test this", "validate", "check if it works"
  • After component implementation is complete
  • User asks "does it look right?"
  • User mentions "browser", "Chrome", or "DevTools"
  • Component is ready for QA
  • Before submitting for review

Decision Framework

Before validating in browser, determine:

What Needs Validation?

1. **Responsive behavior** → Test layout at 320px, 768px, 1024px breakpoints 2. **Accessibility** → Check contrast, keyboard nav, ARIA, focus indicators 3. **Interactions** → Test hover, click, focus states 4. **Visual accuracy** → Compare with design reference (if provided) 5. **Functionality** → Verify buttons, forms, links work correctly

What Are the Test URLs?

**Local development**:

  • `http://localhost:8000/component`
  • `http://site.ddev.site/test-page`
  • `http://site.test/node/123`

**Staging/production**:

  • `https://staging.example.com/feature`
  • `https://production.com/public-page`

**URL must be**:

  • Accessible from your machine
  • Fully loaded (not 404, not auth-protected)
  • Stable (not constantly changing)

What Breakpoints to Test?

**Standard breakpoints** (always test):

  • ✅ **Mobile**: 320px x 568px (minimum, iPhone SE)
  • ✅ **Tablet**: 768px x 1024px (iPad)
  • ✅ **Desktop**: 1024px x 768px (laptop)
  • ⚠️ **Large desktop**: 1920px x 1080px (optional)

**What to check at each breakpoint**:

  • Layout doesn't break
  • No horizontal scrolling
  • Text is readable (no overflow)
  • Touch targets ≥ 44px (mobile), ≥ 40px (desktop)
  • Images don't extend beyond viewport

What Accessibility Checks?

**WCAG 2.1 Level AA (always check)**:

  • ✅ **Color contrast**: Calculate exact ratios (4.5:1 normal, 3:1 large)
  • ✅ **Keyboard navigation**: Tab through all interactive elements
  • ✅ **Focus indicators**: Visible 2px minimum
  • ✅ **Semantic HTML**: Proper headings, landmarks, ARIA
  • ✅ **Alt text**: Content images have descriptive alt, decorative have alt=""

**How to test**:

  • Use `mcp__chrome-devtools__press_key` to Tab through page
  • Use `mcp__chrome-devtools__take_snapshot` to check DOM structure
  • Calculate contrast ratios from screenshots

What Interactions to Test?

**Interactive states**:

  • `:hover` - Use `mcp__chrome-devtools__hover` on elements
  • `:focus` - Tab to elements with keyboard
  • `:active` - Click elements with `mcp__chrome-devtools__click`

**Capture screenshots**:

  • Initial state
  • Each breakpoint
  • Hover/focus states
  • Any dynamic behavior

What Errors to Check?

**Console errors**:

  • Use `mcp__chrome-devtools__list_console_messages`
  • Check for JavaScript errors
  • Report with stack traces

**Network issues**:

  • Use `mcp__chrome-devtools__list_network_requests`
  • Check for 404s, failed requests
  • Note slow-loading resources

Decision Tree

User requests browser validation
    ↓
Check: Chrome DevTools MCP available?
    ↓ Yes
Navigate to test URL
    ↓
Test each breakpoint (320/768/1024px)
    ↓
Capture screenshots at each breakpoint
    ↓
Check accessibility (contrast/keyboard/ARIA)
    ↓
Test interactions (hover/focus/click)
    ↓
Check console & network errors
    ↓
Generate detailed technical report

Required MCP Integration

This skill requires **Chrome DevTools MCP** integration. Correct tool names to use:

**Navigation & Pages**:

  • `mcp__chrome-devtools__navigate_page` - Navigate to URL
  • `mcp__chrome-devtools__list_pages` - Get available pages
  • `mcp__chrome-devtools__new_page` - Create new tab

**Viewport & Screenshots**:

  • `mcp__chrome-devtools__resize_page` - Change viewport size
  • `mcp__chrome-devtools__take_screenshot` - Capture screenshot
  • `mcp__chrome-devtools__take_snapshot` - Get DOM structure

**Interaction**:

  • `mcp__chrome-devtools__click` - Click element by UID
  • `mcp__chrome-devtools__hover` - Hover over element
  • `mcp__chrome-devtools__fill` - Fill form field
  • `mcp__chrome-devtools__press_key` - Press keyboard key

**Debugging**:

  • `mcp__chrome-devtools__list_console_messages` - Get JavaScript errors
  • `mcp__chrome-devtools__list_network_requests` - Check network activity

Validation Process

Phase 1: Initial Setup

// Navigate to test page
await mcp__chrome-devtools__navigate_page({
  url: testUrl,
  type: "url"
});

// Wait for page load (built-in)

// Take initial full-page screenshot
await mcp__chrome-devtools__take_screenshot({
  filePath: "screenshots/component/initial-fullpage.png",
  fullPage: true
});

// Get page structure
const pageSnapshot = await mcp__c
Read more
@kanopi
Ships withcms-cultivator

Specialist agents and auto-invoked skills for Drupal/WordPress development. Works in Claude Code, Claude Desktop, and OpenAI Codex. Full documentation: What changed in 2.0? CMS Cultivator now focuses on CMS development workflows.

1728 skills1 agent
Get the whole plugin

Stars on GitHub

Momentum

stars in total
17
Star history of kanopi/cms-cultivator on GitHub, a chart by star-history.com

Other skills on cms-cultivator.

coverage-analyzer

coverage-analyzer

Automatically analyze test coverage when user asks which code is tested, mentions coverage gaps, or shows code asking about…

ddev-docker-cleanup

ddev-docker-cleanup

Deterministic cleanup of DDEV and Docker disk usage on OrbStack, Docker Desktop, or any Docker provider. Safely reclaims space by…

ddev-workflow

ddev-workflow

Operate a Kanopi DDEV site day to day — get a fresh clone or worktree actually serving pages, pull a database from the hosting…

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills10d309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels,…

ecc11d293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits…

react1d252k
@facebook@facebookInstall Skill

Questions about browser-validator.

Which coding agents can use browser-validator?
browser-validator installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.