agent-browser

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

Updated Dec 9, 2025
One-click install
npx skills add https://github.com/Aki2022/skills --skill agent-browser-aki2022
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Aki2022/skills/tree/main/agent-browser
Command: npx skills add https://github.com/Aki2022/skills --skill agent-browser-aki2022

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agent-browser.

What problem does it solve? Manually testing web apps, filling forms, scraping pages, and checking Slack or Electron apps is repetitive and error-prone. This Skill gives AI agents a fast CLI to drive Chrome/Chromium directly, so any browser task can be scripted and repeated reliably. ## Core Features & Use Cases - Browser Automation: Navigate pages, click buttons, fill forms, take screenshots, and extract data using accessibility-tree snapshots with compact element refs. - Specialized Targets: Automate Electron desktop apps (VS Code, Slack, Discord, Figma), manage Slack workspaces, run exploratory QA and dogfooding sessions, or execute in Vercel Sandbox microVMs and AWS Bedrock AgentCore cloud browsers. - Session Management: Persist sessions, authentication vaults, state, and video recordings across runs. - Use Case: Ask the agent to log into your web app, walk through the checkout flow, capture screenshots at each step, and report any broken elements during a bug hunt. ## Quick Start Install the CLI with npm i -g agent-browser, then ask the agent to open a website and take a screenshot using agent-browser.

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 agent-browser globally with npm, run agent-browser install, then load workflow instructions via agent-browser skills get core. The CLI exposes commands for navigation, clicking, form filling, screenshots, and data extraction using accessibility-tree element refs.

What browser automation tool works without Playwright or Puppeteer?

agent-browser is a native Rust CLI that drives Chrome and Chromium directly over the Chrome DevTools Protocol, with no Playwright or Puppeteer dependency. It provides accessibility-tree snapshots with compact element refs for reliable interaction.

Can agent-browser automate Electron 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 instructions with agent-browser skills get electron, or use skills get slack for Slack workspace automation.

Does agent-browser work in cloud or sandboxed environments?

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

Which AI coding agents are compatible with agent-browser?

agent-browser works with any AI agent that can run shell commands, including Cursor, Claude Code, Codex, Continue, and Windsurf. The CLI serves version-matched skill content so instructions stay in sync with the installed release.