IMPORTANT - Path Resolution: This skill can be installed in different locations (plugin system, manual installation, global, or project-specific). Before executing any commands, determine the skill directory based on where you loaded this SKILL.md file, and use that path in all commands below. Replace $SKILL_DIR with the actual discovered path.

Common installation paths:

• Plugin system: ~/.claude/plugins/marketplaces/playwright-skill/skills/playwright-skill
• Manual global: ~/.claude/skills/playwright-skill
• Project-specific: <project>/.claude/skills/playwright-skill

Playwright Browser Automation

General-purpose browser automation skill. I'll write custom Playwright code for any automation task you request and execute it via the universal executor.

CRITICAL WORKFLOW - Follow these steps in order:

1. Auto-detect dev servers - For localhost testing, ALWAYS run server detection FIRST:

   cd $SKILL_DIR && node -e "require('./lib/helpers').detectDevServers().then(servers => console.log(JSON.stringify(servers)))"
   

   • If 1 server found: Use it automatically, inform user
   • If multiple servers found: Ask user which one to test
   • If no servers found: Ask for URL or offer to help start dev server

2. Write scripts to /tmp - NEVER write test files to skill directory; always use /tmp/playwright-test-*.js

3. Use visible browser by default - Always use headless: false unless user specifically requests headless mode

4. Parameterize URLs - Always make URLs configurable via environment variable or constant at top of script

How It Works

1. You describe what you want to test/automate
2. I auto-detect running dev servers (or ask for URL if testing external site)
3. I write custom Playwright code in /tmp/playwright-test-*.js (won't clutter your project)
4. I execute it via: cd $SKILL_DIR && node run.js /tmp/playwright-test-*.js
5. Results displayed in real-time, browser window visible for debugging
6. Test files auto-cleaned from /tmp by your OS

Setup (First Time)

cd $SKILL_DIR
npm run setup

This installs Playwright and Chromium browser. Only needed once.

Browser Modes

Default: Connect to User's Chrome (Recommended)

Uses connectToChrome() to connect to Chrome with your existing profile (cookies, sessions, login state). This is the preferred method when testing authenticated apps.

const helpers = require('./lib/helpers');

const { browser, page } = await helpers.connectToChrome();
// Your cookies and sessions are available!
await page.goto('http://localhost:3000/dashboard');

How it works:

• Launches Chrome with a dedicated ~/playwright-agent profile via CDP (port 9222)
• If Chrome debug instance isn't running, it launches automatically
• Runs alongside your normal Chrome (separate instance)
• First time: log into your app in this Chrome window; sessions persist for future runs

Manual launch (if needed):

open -na "Google Chrome" --args --remote-debugging-port=9222 --user-data-dir="$HOME/playwright-agent"

Alternative: Clean Browser Instance

For tests that need a fresh browser without any state:

const { chromium } = require('playwright');
const browser = await chromium.launch({ headless: false });
const page = await browser.newPage();

Execution Pattern

Step 1: Detect dev servers (for localhost testing)

cd $SKILL_DIR && node -e "require('./lib/helpers').detectDevServers().then(s => console.log(JSON.stringify(s)))"

Step 2: Write test script to /tmp with URL parameter

// /tmp/playwright-test-page.js
const helpers = require('./lib/helpers');

// Parameterized URL (detected or user-provided)
const TARGET_URL = 'http://localhost:3001'; // <-- Auto-detected or from user

(async () => {
  const { browser, page } = await helpers.connectToChrome();

  await page.goto(TARGET_URL);
  console.log('Page loaded:', await page.title());

  await page.screenshot({ path: '/tmp/screenshot.png', fullPage: true });
  console.log('📸 Screenshot saved to /tmp/screenshot.png');

  // Note: Don't close browser - keeps Chrome running for next automation
})();

Step 3: Execute from skill directory

cd $SKILL_DIR && node run.js /tmp/playwright-test-page.js

Common Patterns

Test a Page (Multiple Viewports)

// /tmp/playwright-test-responsive.js
const { chromium } = require('playwright');

const TARGET_URL = 'http://localhost:3001'; // Auto-detected

(async () => {
  const browser = await chromium.launch({ headless: false, slowMo: 100 });
  const page = await browser.newPage();

  // Desktop test
  await page.setViewportSize({ width: 1920, height: 1080 });
  await page.goto(TARGET_URL);
  console.log('Desktop - Title:', await page.title());
  await page.screenshot({ path: '/tmp/desktop.png', fullPage: true });

  // Mobile test
  await page.setViewportSize({ width: 375, height: 667 });
  await page.screenshot({ path: '/tmp/mobile.png', fullPage: true });

  await browser.close();
})();

Test Login Flow

// /tmp/playwright-test-login.js
const { chromium } = require('playwright');

const TARGET_URL = 'http://localhost:3001'; // Auto-detected

(async () => {
  const browser = await chromium.launch({ headless: false });
  const page = await browser.newPage();

  await page.goto(`${TARGET_URL}/login`);

  await page.fill('input[name="email"]', 'test@example.com');
  await page.fill('input[name="password"]', 'password123');
  await page.click('button[type="submit"]');

  // Wait for redirect
  await page.waitForURL('**/dashboard');
  console.log('✅ Login successful, redirected to dashboard');

  await browser.close();
})();

Fill and Submit Form

// /tmp/playwright-test-form.js
const { chromium } = require('playwright');

const TARGET_URL = 'http://localhost:3001'; // Auto-detected

(async () => {
  const browser = await chromium.launch({ headless: false, slowMo: 50 });
  const page = await browser.newPage();

  await page.goto(`${TARGET_URL}/contact`);

  await page.fill('input[name="name"]', 'John Doe');
  await page.fill('input[name="email"]', 'john@example.com');
  await page.fill('textarea[name="message"]', 'Test message');
  await page.click('button[type="submit"]');

  // Verify submission
  await page.waitForSelector('.success-message');
  console.log('✅ Form submitted successfully');

  await browser.close();
})();

Check for Broken Links

const { chromium } = require('playwright');

(async () => {
  const browser = await chromium.launch({ headless: false });
  const page = await browser.newPage();

  await page.goto('http://localhost:3000');

  const links = await page.locator('a[href^="http"]').all();
  const results = { working: 0, broken: [] };

  for (const link of links) {
    const href = await link.getAttribute('href');
    try {
      const response = await page.request.head(href);
      if (response.ok()) {
        results.working++;
      } else {
        results.broken.push({ url: href, status: response.status() });
      }
    } catch (e) {
      results.broken.push({ url: href, error: e.message });
    }
  }

  console.log(`✅ Working links: ${results.working}`);
  console.log(`❌ Broken links:`, results.broken);

  await browser.close();
})();

Take Screenshot with Error Handling

const { chromium } = require('playwright');

(async () => {
  const browser = await chromium.launch({ headless: false });
  const page = await browser.newPage();

  try {
    await page.goto('http://localhost:3000', {
      waitUntil: 'networkidle',
      timeout: 10000
    });

    await page.screenshot({
      path: '/tmp/screenshot.png',
      fullPage: true
    });

    console.log('📸 Screenshot saved to /tmp/screenshot.png');
  } catch (error) {
    console.error('❌ Error:', error.message);
  } finally {
    await browser.close();
  }
})();

Test Responsive Design

// /tmp/playwright-test-responsive-full.js
const { chromium } = require('playwright');

const TARGET_URL = 'http://localhost:3001'; // Auto-detected

(async () => {
  const browser = await chromium.launch({ headless: false });
  const page = await browser.newPage();

  const viewports = [
    { name: 'Desktop', width: 1920, height: 1080 },
    { name: 'Tablet', width: 768, height: 1024 },
    { name: 'Mobile', width: 375, height: 667 }
  ];

  for (const viewport of viewports) {
    console.log(`Testing ${viewport.name} (${viewport.width}x${viewport.height})`);

    await page.setViewportSize({
      width: viewport.width,
      height: viewport.height
    });

    await page.goto(TARGET_URL);
    await page.waitForTimeout(1000);

    await page.screenshot({
      path: `/tmp/${viewport.name.toLowerCase()}.png`,
      fullPage: true
    });
  }

  console.log('✅ All viewports tested');
  await browser.close();
})();

Inline Execution (Simple Tasks)

For quick one-off tasks, you can execute code inline without creating files:

# Take a quick screenshot
cd $SKILL_DIR && node run.js "
const browser = await chromium.launch({ headless: false });
const page = await browser.newPage();
await page.goto('http://localhost:3001');
await page.screenshot({ path: '/tmp/quick-screenshot.png', fullPage: true });
console.log('Screenshot saved');
await browser.close();
"

When to use inline vs files:

• Inline: Quick one-off tasks (screenshot, check if element exists, get page title)
• Files: Complex tests, responsive design checks, anything user might want to re-run

Available Helpers

Utility functions in lib/helpers.js:

const helpers = require('./lib/helpers');

// Connect to Chrome with your profile (cookies, sessions preserved)
const { browser, page } = await helpers.connectToChrome();

// Detect running dev servers (CRITICAL - use this first!)
const servers = await helpers.detectDevServers();
console.log('Found servers:', servers);

// Safe click with retry
await helpers.safeClick(page, 'button.submit', { retries: 3 });

// Safe type with clear
await helpers.safeType(page, '#username', 'testuser');

// Take timestamped screenshot
await helpers.takeScreenshot(page, 'test-result');

// Handle cookie banners
await helpers.handleCookieBanner(page);

// Extract table data
const data = await helpers.extractTableData(page, 'table.results');

See lib/helpers.js for full list.

Advanced Usage

For comprehensive Playwright API documentation, see API_REFERENCE.md:

• Selectors & Locators best practices
• Network interception & API mocking
• Authentication & session management
• Visual regression testing
• Mobile device emulation
• Performance testing
• Debugging techniques
• CI/CD integration

Tips

• CRITICAL: Detect servers FIRST - Always run detectDevServers() before writing test code for localhost testing
• Use /tmp for test files - Write to /tmp/playwright-test-*.js, never to skill directory or user's project
• Parameterize URLs - Put detected/provided URL in a TARGET_URL constant at the top of every script
• DEFAULT: Visible browser - Always use headless: false unless user explicitly asks for headless mode
• Headless mode - Only use headless: true when user specifically requests "headless" or "background" execution
• Slow down: Use slowMo: 100 to make actions visible and easier to follow
• Error handling: Always use try-catch for robust automation
• Console output: Use console.log() to track progress and show what's happening

Wait Strategies

NEVER use networkidle - it's extremely slow and unnecessary.

Primary approach: Wait for a specific element you know should appear:

await page.goto(url);
await page.locator('.dashboard').waitFor();  // or any element you expect to see

Fallback: If you don't know what element to wait for, use default load:

await page.goto(url);  // uses 'load' by default, which is fine

Decision guide:

• Know what element should appear? → Wait for that selector
• Don't know the page structure? → Just use page.goto(url) with default load
• Need to interact with an element? → Playwright auto-waits on locator actions

Avoid:

// DON'T do this - extremely slow
await page.goto(url, { waitUntil: 'networkidle' });

Troubleshooting

Playwright not installed:

cd $SKILL_DIR && npm run setup

Module not found: Ensure running from skill directory via run.js wrapper

Browser doesn't open: Check headless: false and ensure display available

Element not found: Add wait: await page.waitForSelector('.element', { timeout: 10000 })

Example Usage

User: "Test if the marketing page looks good"

Claude: I'll test the marketing page across multiple viewports. Let me first detect running servers...
[Runs: detectDevServers()]
[Output: Found server on port 3001]
I found your dev server running on http://localhost:3001

[Writes custom automation script to /tmp/playwright-test-marketing.js with URL parameterized]
[Runs: cd $SKILL_DIR && node run.js /tmp/playwright-test-marketing.js]
[Shows results with screenshots from /tmp/]

User: "Check if login redirects correctly"

Claude: I'll test the login flow. First, let me check for running servers...
[Runs: detectDevServers()]
[Output: Found servers on ports 3000 and 3001]
I found 2 dev servers. Which one should I test?
- http://localhost:3000
- http://localhost:3001

User: "Use 3001"

[Writes login automation to /tmp/playwright-test-login.js]
[Runs: cd $SKILL_DIR && node run.js /tmp/playwright-test-login.js]
[Reports: ✅ Login successful, redirected to /dashboard]

Notes

• Each automation is custom-written for your specific request
• Not limited to pre-built scripts - any browser task possible
• Auto-detects running dev servers to eliminate hardcoded URLs
• Test scripts written to /tmp for automatic cleanup (no clutter)
• Code executes reliably with proper module resolution via run.js
• Progressive disclosure - API_REFERENCE.md loaded only when advanced features needed