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 extract data without writing custom automation scripts. ## 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: Includes dedicated skills for Electron desktop apps (VS Code, Slack, Discord, Figma), Slack workspace automation, exploratory testing and QA, Vercel Sandbox microVMs, and AWS Bedrock AgentCore cloud browsers. - Session Management: Supports sessions, an authentication vault, state persistence, video recording, and an observability dashboard on port 4848. - Use Case: Ask the agent to log into a web app, fill out a multi-step form, take a screenshot of the result, and extract confirmation data — all executed through the agent-browser CLI. ## Quick Start Install the CLI with npm i -g agent-browser, run agent-browser install, then ask the agent to open a website and take a screenshot.