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.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
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.
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 $SKILL_DIR with the actual discovered path.
General-purpose browser automation skill. I'll write custom Playwright code for any automation task you request and execute it via the universal executor.
CRITICAL WORKFLOW - Follow these steps in order:
Auto-detect dev servers - For localhost testing, ALWAYS run server detection FIRST:
For comprehensive Playwright API documentation, see API_REFERENCE.md:
Selectors & Locators best practices
Network interception & API mocking
Authentication & session management
Visual regression testing
Mobile device emulation
Performance testing
Debugging techniques
CI/CD integration
Tips
CRITICAL: Detect servers FIRST - Always run detectDevServers() before writing test code for localhost testing
Custom headers - Use PW_HEADER_NAME/PW_HEADER_VALUE env vars to identify automated traffic to your backend
Use /tmp for test files - Write to /tmp/playwright-test-*.js, never to skill directory or user's project
Parameterize URLs - Put detected/provided URL in a TARGET_URL constant at the top of every script
DEFAULT: Visible browser - Always use headless: false unless user explicitly asks for headless mode
Headless mode - Only use headless: true when user specifically requests "headless" or "background" execution
Slow down: Use slowMo: 100 to make actions visible and easier to follow
Wait strategies: Use waitForURL, waitForSelector, waitForLoadState instead of fixed timeouts
Error handling: Always use try-catch for robust automation
Console output: Use console.log() to track progress and show what's happening
Troubleshooting
Playwright not installed:
cd$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: โ 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
When to Use
This skill is applicable to execute the workflow or actions described in the overview.
