What problem does it solve? AI agents need a reliable way to interact with websites—navigating pages, filling forms, clicking buttons, and extracting data—without heavy dependencies like Playwright or Puppeteer. This Skill provides a fast native CLI that drives Chrome/Chromium over CDP and exposes page elements through compact accessibility-tree references. ## Core Features & Use Cases - Browser Automation: Navigate pages, fill forms, click buttons, take screenshots, and scrape data using stable @eN element refs from accessibility-tree snapshots. - Session & State Management: Persistent sessions, an authentication vault, state persistence, and video recording for repeatable workflows. - Specialized Skills: Load dedicated workflows for Electron desktop apps (VS Code, Slack, Discord, Figma), Slack workspace automation, exploratory QA/dogfooding, HAR-to-API-client derivation, Vercel Sandbox microVMs, and AWS Bedrock AgentCore cloud browsers. - Use Case: Ask your agent to log into a staging web app, walk through the checkout flow, capture screenshots of each step, and report any broken UI elements during a QA pass. ## Quick Start Install the CLI with npm, run agent-browser install, then ask your agent to load the core workflow with agent-browser skills get core before automating any website.
