agent-browser

Automates browser interactions via a CLI using Chrome DevTools Protocol and accessibility-tree snapshots.

Updated Aug 5, 2024
One-click install
npx skills add https://github.com/SethyRung/movie-next --skill agent-browser-sethyrung
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/SethyRung/movie-next/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/SethyRung/movie-next --skill agent-browser-sethyrung

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agent-browser.

What problem does it solve? AI agents need a reliable way to interact with live websites—navigating pages, filling forms, clicking buttons, and extracting data—without brittle selectors or heavyweight frameworks. This Skill provides a fast CLI that drives Chrome/Chromium over CDP with accessibility-tree snapshots and stable element references. ## Core Features & Use Cases - Browser Automation: Navigate pages, fill forms, click elements, take screenshots, and scrape data using compact @eN element refs from accessibility-tree snapshots. - Specialized Targets: Automate Electron desktop apps (VS Code, Slack, Discord, Figma), manage Slack workspaces, run exploratory QA and dogfooding sessions, and operate cloud browsers in Vercel Sandbox microVMs or AWS Bedrock AgentCore. - Sessions & State: Persist sessions, authentication vaults, and video recordings across runs. - Use Case: Ask the agent to log into a staging web app, walk through the checkout flow, capture screenshots at each step, and report any broken interactions. ## Quick Start Ask the agent to open a website with agent-browser, sign in, and take a screenshot of the dashboard.

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 agent-browser?

Install it globally with npm i -g agent-browser, run agent-browser install, then load workflow instructions via agent-browser skills get core. The CLI drives Chrome over CDP and exposes elements as @eN refs from accessibility-tree snapshots.

What browser automation tool works without Playwright or Puppeteer?

agent-browser is a native Rust CLI that controls Chrome/Chromium directly through the Chrome DevTools Protocol, with no Playwright or Puppeteer dependency. It uses accessibility-tree snapshots for reliable element targeting.

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

Yes, load the Electron skill with agent-browser skills get electron to automate desktop apps such as VS Code, Slack, Discord, Figma, Notion, and Spotify. A dedicated Slack skill also covers unreads, messages, and conversation search.

Does agent-browser support cloud browsers?

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

How do I keep agent-browser instructions up to date?

Run agent-browser skills get core before each session. The CLI serves skill content matching the installed version, so workflow instructions never go stale, and skills list shows everything available.