agent-browser

Automates browser interactions via Chrome DevTools Protocol with accessibility-tree snapshots.

2|2|Updated Dec 23, 2017
One-click install
npx skills add https://github.com/xriu/dotfiles --skill agent-browser-xriu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/xriu/dotfiles/tree/main/home/.skills/agent-browser
Command: npx skills add https://github.com/xriu/dotfiles --skill agent-browser-xriu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agent-browser.

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. ## Core Features & Use Cases - Browser Automation via CDP: Control Chrome/Chromium directly through the DevTools Protocol with accessibility-tree snapshots and compact element refs for reliable interaction. - Specialized Workflows: Automate Electron desktop apps (VS Code, Slack, Discord, Figma), manage Slack workspaces, run exploratory QA testing, and operate cloud browsers in Vercel Sandbox or AWS Bedrock AgentCore. - Session Management: Use sessions, an authentication vault, state persistence, and video recording for repeatable automation. - Use Case: Ask your agent to log into a web app, fill out a multi-step form, take a screenshot of the result, and extract the confirmation data for a QA report. ## Quick Start Install the CLI with npm, run agent-browser install, then ask your agent to load the core skill with agent-browser skills get core before automating any website.

Frequently Asked Questions about agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser tasks with an AI agent?▼

Install the agent-browser CLI globally with npm, run agent-browser install, then load workflow instructions with agent-browser skills get core. The CLI controls Chrome or Chromium via CDP and returns accessibility-tree snapshots with element refs for interaction.

What is the difference between agent-browser and Playwright or Puppeteer?▼

agent-browser is a native Rust CLI that talks to Chrome/Chromium directly over the DevTools Protocol, so it has no Playwright or Puppeteer dependency. It exposes accessibility-tree snapshots with compact element refs designed for AI agent consumption.

Can agent-browser automate Electron desktop apps like VS Code or Slack?▼

Yes, agent-browser supports Electron desktop apps including VS Code, Slack, Discord, Figma, Notion, and Spotify. Load the dedicated Electron workflow with agent-browser skills get electron before driving those applications.

Does agent-browser work with cloud browsers or sandboxed environments?▼

Yes, it supports running inside Vercel Sandbox microVMs and AWS Bedrock AgentCore cloud browsers. Load the corresponding specialized skill with agent-browser skills get vercel-sandbox or agent-browser skills get agentcore.

Why should I run agent-browser skills get core before automation?▼

The SKILL.md file is only a discovery stub; the actual usage guide is served by the CLI itself. Running skills get core loads workflow content that always matches the installed version, so instructions never go stale.