What problem does it solve? Manually testing websites, filling repetitive web forms, and scraping page data is slow and error-prone. This Skill provides a persistent command-line browser that an AI agent can drive step by step to navigate pages, interact with elements, and extract information. ## Core Features & Use Cases - Persistent Browser Sessions: The browser stays open between commands, supporting multi-step workflows with named sessions, tabs, and multiple browser modes (headless Chromium, real Chrome with your profiles, or cloud browsers). - Element-Level Interaction: Inspect pages with browser-use state to get clickable element indices, then click, type, select dropdowns, hover, or send keyboard shortcuts. - Data Extraction & Screenshots: Capture full-page screenshots, run JavaScript, read element text and attributes, manage cookies, and execute stateful Python against the live page. - Cloud Agents & Tunnels: Run autonomous remote browser tasks in parallel, expose local dev servers through tunnels, and sync Chrome profile cookies for authenticated browsing. - Use Case: Test a local web app by starting your dev server, creating a tunnel, opening the tunnel URL in a cloud browser, filling the login form, and capturing a screenshot to verify the result. ## Quick Start Ask the agent to open a website with browser-use, list the clickable elements on the page, and take a screenshot of the result.
