What problem does it solve? Manually navigating websites, filling forms, and extracting page data is repetitive and error-prone. This Skill lets an AI agent drive a real browser through a command-line interface, handling navigation, element interaction, screenshots, and data extraction without writing custom automation code. ## Core Features & Use Cases - Element Interaction via Refs: Snapshot pages to get interactive element references, then click, fill, select, hover, or drag elements by ref or semantic locators (role, text, label, testid). - Capture & Recording: Take full-page screenshots, export pages as PDF, and record video of browser sessions for debugging or documentation. - Sessions, State & Network Control: Run parallel isolated sessions, save and reuse authentication state, manage cookies and localStorage, and intercept or mock network requests. - Use Case: Test a login flow by opening the page, snapshotting interactive elements, filling credentials, submitting the form, waiting for the dashboard URL, and saving the authenticated state for later runs. ## 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.
