What problem does it solve? Manually interacting with websites for testing, scraping, or repetitive form entry is slow and error-prone. This Skill gives an AI agent a deterministic command-line interface to drive a real browser, so tasks like logging in, clicking through flows, and capturing page content become scripted and repeatable. ## Core Features & Use Cases - Snapshot-and-Ref Interaction: Get compact accessibility snapshots with element refs (@e1, @e2) to click, fill, select, and verify page elements without parsing raw HTML. - Session & State Management: Run isolated parallel sessions, save and restore authentication state, and persist cookies/localStorage across runs. - Capture & Extraction: Take full-page screenshots, save pages as PDF, record video of automation runs, and extract text or structured data. - Use Case: Automate a login flow once, save the auth state to a file, then reuse it in later runs to scrape a protected dashboard and capture a screenshot as evidence. ## Quick Start Ask the agent to open a website with agent-browser, snapshot the interactive elements, fill in the login form, and take a screenshot of the result.
