What problem does it solve? Playwright test suites often suffer from flaky tests, brittle selectors, and inconsistent patterns. This Skill routes the AI to the right reference document for the task at hand, so tests follow proven practices for locators, assertions, fixtures, and CI/CD instead of ad-hoc guesses. ## Core Features & Use Cases - Activity-based reference routing: Maps 57 reference documents across 8 categories (core, debugging, testing patterns, advanced, browser APIs, architecture, frameworks, infrastructure/CI-CD) to the user's current task. - Broad scenario coverage: E2E, component, API, visual regression, accessibility (axe-core), security, performance, mobile, i18n, Electron, and browser extension testing. - Debugging and flakiness guidance: Trace viewer usage, flaky test diagnosis, race conditions, console error monitoring, and test isolation. - Use Case: Ask the AI to fix a flaky login test or add accessibility checks to a checkout flow, and it loads the relevant references (e.g., flaky-tests.md, accessibility.md) to produce robust, auto-waiting test code. ## Quick Start Ask the AI to write or fix a Playwright test, such as fixing a flaky login test or adding accessibility tests to the checkout page.