What problem does it solve? Manually driving a browser to test web pages, debug failing Playwright tests, or capture page state is slow and repetitive. This Skill lets an AI agent control a real browser session through playwright-cli commands, turning every action into reusable Playwright TypeScript code. ## Core Features & Use Cases - Browser Automation: Open pages, click, fill forms, navigate tabs, and capture snapshots using element refs from accessibility snapshots. - Test Authoring and Healing: Explore an app, generate Playwright test specs and test files from recorded actions, and debug failing tests by attaching to paused test sessions. - Network and Storage Control: Mock API requests, manage cookies and localStorage, save and restore authentication state, and record traces or videos of sessions. - Use Case: A developer has a failing Playwright test. Run it with --debug=cli, attach playwright-cli to the paused session, inspect the live page with snapshots and console logs, rehearse the fix, and paste the generated code back into the test. ## Quick Start Ask the agent to open a website with playwright-cli, take a snapshot of the page, and click or fill elements using the refs shown in the snapshot.