What problem does it solve? Manually driving a browser to test web pages, debug failing Playwright tests, or record automation flows is slow and repetitive. This Skill lets an AI agent control a real browser through simple CLI commands, capturing snapshots, generating test code, and diagnosing failures without writing boilerplate. ## Core Features & Use Cases - Browser Automation: Open pages, click, fill forms, drag, upload files, manage tabs, and handle dialogs using element refs from accessibility snapshots. - Test Authoring & Healing: Run Playwright tests in debug mode, attach to the paused session, and turn every CLI action into copy-pasteable TypeScript test code following a plan-generate-heal workflow. - Debugging & Inspection: Capture traces, record annotated videos, mock network requests, inspect console output, and manage cookies, localStorage, and session state. - Use Case: A failing login test needs fixing. Run it with --debug=cli, attach playwright-cli to the paused session, snapshot the page to find the renamed button, rehearse the corrected click, and paste the generated locator code back into the test. ## Quick Start Use playwright-cli to open https://example.com, take a snapshot, and click the sign-in button.