skills.rest
pattobrien
pattobrienCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

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

2|Updated Oct 16, 2021
Search Tags:#screenshots#browser automation#web scraping#slack#electron#qa testing#chrome devtools protocol
One-click install
npx skills add https://github.com/pattobrien/dotfiles --skill agent-browser-pattobrien
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/pattobrien/dotfiles/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/pattobrien/dotfiles --skill agent-browser-pattobrien

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agent-browser.

What problem does it solve? AI agents need a programmatic way to interact with websites and desktop apps—navigating pages, filling forms, clicking elements, and capturing screenshots—without relying on heavyweight frameworks like Playwright or Puppeteer. ## Core Features & Use Cases - Browser Automation via CDP: Controls Chrome/Chromium through the DevTools Protocol with accessibility-tree snapshots and compact @eN element refs for reliable interaction. - Specialized Workflows: Supports Electron desktop apps (VS Code, Slack, Discord, Figma), Slack workspace automation, exploratory QA testing, HAR-to-API-client derivation, Vercel Sandbox microVMs, and AWS Bedrock AgentCore cloud browsers. - Sessions & Observability: Provides session persistence, an authentication vault, video recording, and an independent dashboard on port 4848. - Use Case: Ask your agent to log into a web app, fill out a signup form, take a screenshot of the result, and verify the flow works end to end. ## Quick Start Install the CLI with npm i -g agent-browser, run agent-browser install, then ask your agent to load the core workflow 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 agent-browser globally with npm i -g agent-browser, run agent-browser install, then load workflow instructions with agent-browser skills get core. The CLI controls Chrome via CDP and exposes element refs for clicking, typing, and navigation.

What browser automation tool works without Playwright or Puppeteer?▼

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

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 workflow with agent-browser skills get electron before automating these apps.

Does agent-browser support Slack message automation?▼

Yes, it can check Slack unreads, send Slack messages, and search Slack conversations. Load the Slack-specific instructions with agent-browser skills get slack on the installed CLI version.

Can agent-browser run in cloud environments or sandboxes?▼

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

Why should agents use the dashboard on port 4848?▼

The observability dashboard runs independently of browser sessions on port 4848 and proxies session tabs, status, and stream traffic internally. Agents should stay on the dashboard origin so session ports do not need to be exposed.

Related Skills

Explore More Software Engineering Skills→
MrWest3MrWest3

agent-browser

Automate Chrome/Chromium browser tasks via CDP using a Rust CLI.

Community
Advanced
arthtyagiarthtyagi
1

agent-browser

Automate browser interactions and capture web content across isolated sessions.

Community
Advanced
useatriumuseatrium
4

dogfood

Identify and document bugs, usability problems, accessibility gaps, and console errors in web applications.

Official
Advanced
HouseGarofaloHouseGarofalo
3

browserless

Automate headless Chrome browser tasks via REST API and WebSocket.

Official
Intermediate