Testing skills
Testing skills give your agent the frameworks to write meaningful tests rather than boilerplate coverage, including TDD loops, browser automation, and end-to-end verification.
What your agent can do with testing skills installed
- Run the red-green-refactor loop correctly
- Write resilient Playwright tests with correct selectors, waits, and isolation
- Use the Playwright CLI against a live browser for capture and exploration
- Test React components with appropriate mocking boundaries
- Force a verification pass before declaring a task complete
- Configure Playwright parallelism, retries, and reporting for CI
Skills in this category
Use when implementing any feature or bugfix, before writing implementation code
webapp-testinganthropics/skillsToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
playwright-best-practicescurrents-dev/playwright-best-practices-skillUse when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions, multi-tab/popup flows, mobile/responsive layouts, touch gestures, GraphQL, error handling, offline mode, multi-user collaboration, third-party services (payments, email verification), console error monitoring, global setup/teardown, test annotations (skip, fixme, slow), test tags (@smoke, @fast, @critical, filtering with --grep), project dependencies, security testing (XSS, CSRF, auth), performance budgets (Web Vitals, Lighthouse), iframes, component testing, canvas/WebGL, service workers/PWA, test coverage, i18n/localization, Electron apps, or browser extension testing. Covers E2E, component, API, visual, accessibility, security, Electron, and extension testing.
playwright-climicrosoft/playwright-cliAutomate browser interactions, test web pages and work with Playwright tests.
Works with your agent
Testing skills work with Claude Code, Cursor, GitHub Copilot, Windsurf, Cline, Codex, Gemini CLI, and agents that support the skills CLI.
Frequently asked questions
Will TDD skills stop agents from writing tests that always pass?
They enforce a failing-test-first structure, preventing the agent from reverse-engineering an already-passing implementation.
How do webapp-testing and playwright-best-practices differ?
One covers the full web testing stack; the other focuses on Playwright selectors, fixtures, isolation, and CI.
Can playwright-cli replace Playwright test files?
No. It complements test files by helping with exploration, recording, and element inspection.
Does verification-before-completion slow an agent down?
It adds one final pass, which is usually cheaper than debugging an incorrect completion later.