Use 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.
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
The skill is Playwright test-writing guidance whose only state-changing operation is the `docker compose down -v` teardown in CI test containers, which is disposable task-local infrastructure, so the operational-change gate is only weakly met and no irreversible loss to shared operational state is shown.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The bundled Playwright reference docs are first-party skill content, but the Mailinator example in advanced/third-party.md polls a public inbox where anyone can deliver mail, and the agent extracts text and links from those email bodies.
BigSimmo/PsychSift
fada614
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.