What problem does it solve? Manually interacting with websites for testing, scraping, or repetitive form entry is slow and error-prone, and raw DOM parsing consumes excessive context for AI agents. This Skill provides a CLI-driven browser automation workflow using compact element refs for efficient programmatic web interaction. ## Core Features & Use Cases - Snapshot-Based Interaction: Generate compact snapshots of interactive elements with refs like @e1, then click, fill, select, and check elements directly without parsing full HTML. - Session & State Management: Run parallel isolated sessions, save and restore authentication state, and handle OAuth, 2FA, and cookie-based login flows. - Capture & Extraction: Take full-page screenshots, save pages as PDF, record video sessions, and extract text or structured data from any page. - Use Case: Automate a login flow once, save the auth state to a file, then reuse it across scraping runs to extract product data from a protected dashboard without re-authenticating. ## Quick Start Ask the agent to open a website, snapshot the interactive elements, fill in the login form, and take a screenshot of the result.
