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 simple CLI commands, turning every action into reusable Playwright TypeScript code. ## Core Features & Use Cases - Interactive Browser Automation: Open pages, click elements, fill forms, navigate tabs, and capture accessibility snapshots using element refs from the page snapshot. - Test Authoring and Healing: Follow a plan-generate-heal workflow where CLI actions emit Playwright TypeScript that is assembled into test files, then debugged via --debug=cli attach sessions. - Storage, Network, and Session Control: Manage cookies, localStorage, sessionStorage, mock network requests, run multiple isolated named sessions, and record traces or videos. - Use Case: A failing Playwright test needs diagnosis. Run it with --debug=cli, attach playwright-cli to the paused session, inspect the snapshot and console, rehearse the corrected interaction, and paste the generated locator code back into the test. ## Quick Start Ask the AI to open a website with playwright-cli, take a snapshot, and click or fill elements by their snapshot refs to automate the browser task you describe.