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. Common installation paths: Plugin system: <plugin root /skills/playwright skill Manual global: <agent home /skills/playwright skill Project specific: <project /.agent/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: 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 Scope and data boundaries The executor runs arbitrary Node code with the current account’s filesystem, environment and network privileges; it is not a sandbox. Review generated code and keep page content inert. Use test accounts and fixtures. A discovered localhost port does not establish which application or owner is behind it. Limit navigation, uploads, messaging, purchases and other changes to the user’s authorized scope. Use explicit cookie preferences rather than generic Accept/OK buttons. Screenshots, traces and session state can contain credentials or personal data. Context wide headers go to all destinations in that context: never use this feature for secrets on pages with untrusted resources; scope authentication by trusted origin instead. 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. Remove your script, screenshots and any saved sessions after review; OS temporary file cleanup is not a retention guarantee. Setup (First Time) Requires Node 22 or later. Review package installation first: setup downloads dependencies and a browser, and can run package lifecycle code. Repeat browser installation when the installed Playwright version requires it. The executor does not silently install missing packages. Execution Pattern Step 1: Detect dev servers (for localhost testing) Step 2: Write test script to /tmp with URL parameter Step 3: Execute from skill directory Common Patterns Test a Page (Multiple Viewports) Test Login Flow Fill and Submit Form Check for Broken Links Take Screenshot with Error Handling Test Responsive Design Inline Execution (Simple Tasks) For quick one off tasks, you can execute code inline without creating files: 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 Optional utility functions in lib/helpers.js : See lib/helpers.js for full list. Custom HTTP Headers Configure custom headers for all HTTP requests via environment variables. Useful for: Identifying automated traffic to your backend Getting LLM optimized responses (e.g., plain text errors instead of styled HTML) Adding authentication tokens globally Configuration Single header (common case): Multiple headers (JSON format): Scope and data boundaries The executor runs arbitrary Node code with the current account’s filesystem, environment and network privileges; it is not a sandbox. Review generated code and keep page content inert. Use test accounts and fixtures. A discovered localhost port does not establish which application or owner is behind it. Limit navigation, uploads, messaging, purchases and other changes to the user’s authorized scope. Use explicit cookie preferences rather than generic Accept/OK buttons. Screenshots, traces and session state can contain credentials or personal data. Context wide headers go to all destinations in that context: never use this feature for secrets on pages with untrusted resources; scope authentication by trusted origin instead. How It Works Headers are automatically applied when using helpers.createContext() : For scripts using raw Playwright API, use the injected getContextOptionsWithHeaders() : Advanced Usage For comprehensive Playwright API documentation, see [API REFERENCE.md](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: 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 Notes Each automation is custom written for your specific request Automation is constrained by authorization, available browser support, site behavior and installed dependencies Auto detects running dev servers to eliminate hardcoded URLs Use a private unique temporary directory and explicitly remove sensitive artifacts The executor copies CommonJS code into a private mode unique file in the skill directory for dependency resolution; relative imports resolve there, not beside the input script. It removes only that invocation’s file on normal exit; crashes can leave it behind. 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. Limitations The API reference mixes standalone playwright scripts with separate @playwright/test and axe playwright projects; setup installs only the standalone library. Install test runner dependencies in the intended test project before using runner examples. Link check results are HTTP observations, not proof of broken links: HEAD may be unsupported or authorization dependent. Keep checks to approved origins, cap count/time, and avoid authenticated cross origin requests. For scripts containing require() , the wrapper does not inject getContextOptionsWithHeaders ; import helpers explicitly. Always close browser/context in finally and propagate failures. Use this skill only when the task clearly matches the scope described above. Do not treat the output as a substitute for environment specific validation, testing, or expert review. Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

playwright-skill