from claude-skills-collection13
Run and manage Playwright-based end-to-end test regimes: discovery, execution, evidence capture, and reporting for web apps.
Provides a comprehensive end-to-end testing workflow using Playwright MCP. The skill helps agents set up test regimes, discover user flows, run tests with evidence capture (screenshots, DOM, network), and produce both human and machine-readable reports for failures, regressions, and flaky areas.
Trigger when a user asks to set up or execute automated web tests, analyze flaky failures, or generate reproducible reports. Common triggers: "run E2E tests", "setup test regime", "what failed in tests", "flaky test report". It's meant for web applications where Playwright MCP is available.
Best used by agents integrated with Playwright/automation-capable MCP servers or developer assistants that can orchestrate Playwright runs. Agents that can only provide static advice can still use the run/report guidance manually.
This skill has not been reviewed by our automated audit pipeline yet.
