What problem does it solve? Manually interacting with websites for testing, scraping, or repetitive form entry is slow and error-prone, and raw DOM dumps overwhelm AI agents with tokens. This Skill provides a CLI that lets an AI agent drive a real browser using compact element references instead of parsing full HTML. ## Core Features & Use Cases - Snapshot-Based Interaction: Get interactive elements as compact refs (@e1, @e2) and click, fill, select, or check them directly, reducing context usage dramatically. - Session & State Management: Run isolated parallel sessions, save and restore authentication state, and persist cookies across runs. - Capture & Extraction: Take screenshots, save pages as PDF, record video, extract text, and evaluate JavaScript in the page context. - Use Case: Automate a login flow once, save the auth state to a file, then reuse it across future scraping or testing sessions without re-entering credentials. ## Quick Start Open https://example.com with agent-browser, take an interactive snapshot, and fill out the signup form using the element refs.
