What problem does it solve? Manually driving a browser to test web pages, debug failing Playwright tests, or record automation flows is slow and error-prone. This Skill lets an AI agent control a real browser through the playwright-cli command line, turning every action into reusable Playwright TypeScript code. ## Core Features & Use Cases - Interactive Browser Automation: Open pages, click, fill forms, drag, upload files, manage tabs, and inspect accessibility snapshots using element refs. - Test Authoring and Healing: Run tests with --debug=cli, attach to the paused session, rehearse fixes live, and copy the generated TypeScript back into spec files following a plan-generate-heal workflow. - Network, Storage, and Session Control: Mock requests, manage cookies and localStorage, run multiple isolated named sessions, and attach to running Chrome or Edge instances via CDP. - Use Case: A failing CI test is debugged by running it with --debug=cli, attaching playwright-cli to the paused page, inspecting the snapshot and console, fixing the locator, and rerunning the test until green. ## Quick Start Use the playwright-cli skill to open https://example.com, take a snapshot, and click the sign-in button.