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 via the playwright-cli command line, producing snapshots, generated test code, traces, and recordings without writing boilerplate automation scripts. ## Core Features & Use Cases - Interactive Browser Automation: Open pages, click, fill forms, drag, upload files, and inspect accessibility snapshots using element refs, CSS selectors, or Playwright locators. - Test Plan, Generate, and Heal: Explore an app through a seed test, write spec files, generate Playwright TypeScript tests from recorded actions, and debug or fix failing tests via --debug=cli attach sessions. - Session, Storage, and Network Control: Run isolated named browser sessions, save and restore cookies/localStorage state, mock network requests, capture traces, and record annotated videos. - Use Case: A QA engineer asks the agent to reproduce a login bug: the agent opens the app, fills the form, captures console errors and network requests, then generates a regression test from the recorded actions. ## Quick Start Ask the agent to open a website with playwright-cli, take a snapshot of the page, and click or fill elements by their snapshot refs.