What problem does it solve? Manually interacting with websites for testing, data extraction, or repetitive tasks is slow and error-prone. This Skill gives AI agents programmatic control over Chrome/Chromium browsers to navigate pages, fill forms, click elements, take screenshots, and scrape data without writing custom automation code. ## Core Features & Use Cases - Browser Automation via CDP: Controls Chrome/Chromium directly through the Chrome DevTools Protocol with no Playwright or Puppeteer dependency, using accessibility-tree snapshots and compact element refs for reliable interaction. - Specialized Workflows: Extends beyond web pages to Electron desktop apps (VS Code, Slack, Discord, Figma), Slack workspace automation, exploratory QA testing, Vercel Sandbox microVMs, and AWS Bedrock AgentCore cloud browsers. - Session & State Management: Supports sessions, an authentication vault, state persistence, video recording, and an observability dashboard on port 4848. - Use Case: Imagine you need to test a login flow on your web app. Ask the agent to open the site, fill in credentials, click submit, and capture a screenshot of the result, all through CLI commands. ## Quick Start Ask the agent to open a website with agent-browser, fill out the login form, and take a screenshot of the resulting page.