Executes Playwright end-to-end UI tests and provides detailed summaries of failures with diagnostic artifacts.
This skill enables Claude to manage the full lifecycle of Playwright end-to-end testing, from environment setup and browser installation to executing tests and analyzing failures. It intelligently handles multiple package managers like npm, pnpm, and yarn, enforces headless execution by default, and automatically triggers diagnostic re-runs with traces and screenshots upon failure. By providing a structured summary of test results and direct paths to report artifacts, it streamlines the QA process and helps developers quickly identify and resolve UI regressions within their AI-assisted workflow.
주요 기능
01Intelligent test execution via npm scripts or npx
02Support for headed/headless modes and project-specific filtering
03Diagnostic re-runs with automatic trace and screenshot capture
040 GitHub stars
05Automated browser and dependency management
06Comprehensive pass/fail summaries with artifact path reporting
사용 사례
01Verifying UI changes and frontend features during development
02Debugging failing end-to-end tests with automated trace analysis
03Running regression suites to ensure project stability after code changes
