General-purpose browser automation as a Claude Skill
A Claude Skill that enables Claude to write and execute any Playwright automation on-the-fly - from simple page tests to complex multi-step flows. Packaged as a Claude Code Plugin for easy installation and distribution.
Claude autonomously decides when to use this skill based on your browser automation needs, loading only the minimal information required for your specific task.
- Any Automation Task - Claude writes custom code for your specific request, not limited to pre-built scripts
- Visible Browser by Default - See automation in real-time with headless: false
- Zero Module Resolution Errors - Universal executor ensures proper module access
- Progressive Disclosure - Concise SKILL.md with full API reference loaded only when needed
- Safe Cleanup - Smart temp file management without race conditions
- Comprehensive Helpers - Optional utility functions for common tasks
This skill can be installed via the Claude Code plugin system or manually.
Verify installation by running /help to confirm the skill is available.
Install directly from GitHub to your skills directory:
Global Installation (Available Everywhere):
Project-Specific Installation:
- Download the latest release from GitHub Releases
- Extract to:
- Global: ~/.claude/skills/playwright-skill
- Project: /path/to/your/project/.claude/skills/playwright-skill
- Navigate to the skill directory and run setup:
cd playwright-skill/skills/playwright-skill npm run setup
Run /help to confirm the skill is loaded, then ask Claude to perform a simple browser task like "Test if google.com loads".
After installation, simply ask Claude to test or automate any browser task. Claude will write custom Playwright code, execute it, and return results with screenshots and console output.
- Describe what you want to test or automate
- Claude writes custom Playwright code for the task
- The universal executor (run.js) runs it with proper module resolution
- Browser opens (visible by default) and automation executes
- Results are displayed with console output and screenshots
Default settings:
- Headless: false (browser visible unless explicitly requested otherwise)
- Slow Motion: 100ms for visibility
- Timeout: 30s
- Screenshots: Saved to /tmp/
Claude will automatically load API_REFERENCE.md when needed for comprehensive documentation on selectors, network interception, authentication, visual regression testing, mobile emulation, performance testing, and debugging.
- Node.js >= 14.0.0
- Playwright ^1.48.0 (installed via npm run setup)
- Chromium (installed via npm run setup)
Playwright not installed? Navigate to the skill directory and run npm run setup.
Module not found errors? Ensure automation runs via run.js, which handles module resolution.
Browser doesn't open? Verify headless: false is set. The skill defaults to visible browser unless headless mode is requested.
Install all browsers? Run npm run install-all-browsers from the skill directory.
Skills are modular capabilities that extend Claude's functionality. Unlike slash commands that you invoke manually, skills are model-invoked—Claude autonomously decides when to use them based on your request.
When you ask Claude to test a webpage or automate browser interactions, Claude discovers this skill, loads the necessary instructions, executes custom Playwright code, and returns results with screenshots and console output.
Contributions are welcome. Fork the repository, create a feature branch, make your changes, and submit a pull request. See CONTRIBUTING.md for details.
- Claude Skills - Official announcement from Anthropic
- Claude Code Skills Documentation
- Claude Code Plugins Documentation
- Plugin Marketplaces
- API_REFERENCE.md - Full Playwright documentation
- GitHub Issues
MIT License - see LICENSE file for details.
.png)

