agent-browser

Control Chrome/Chromium and Electron apps via Chrome DevTools Protocol.

64|2|Updated Nov 8, 2021
One-click install
npx skills add https://github.com/FlatbreadLabs/flatbread --skill agent-browser-flatbreadlabs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/FlatbreadLabs/flatbread/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/FlatbreadLabs/flatbread --skill agent-browser-flatbreadlabs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the need for manual browser interaction when AI agents need to complete web-based or desktop app tasks, removing repetitive work from workflows like form filling, data scraping, and application testing.

Core Features & Use Cases

  • Cross-platform browser control: Interact with Chrome/Chromium web pages and Electron desktop apps (VS Code, Slack, Discord, Figma, etc.) via Chrome DevTools Protocol.
  • Specialized automation workflows: Built-in support for Slack workspace automation, exploratory QA testing, Vercel Sandbox microVM execution, and AWS Bedrock AgentCore cloud browsers.
  • Real-world use case: Scrape product pricing from 100 e-commerce pages, automate Slack unread checks, or run regression tests on a web app without manual intervention.

Quick Start

Use the agent-browser skill to navigate to the specified website, fill out the contact form with the provided details, and take a screenshot of the confirmation page.

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 for AI agents across web and desktop apps?

Browser automation for AI agents is achieved by using Chrome DevTools Protocol to interact with web pages and Electron desktop apps programmatically. This enables navigation, form submission, and data scraping without manual input.

Can I use browser automation to control Electron desktop applications like Slack and VS Code?

Yes, browser automation can control Electron desktop applications like Slack, VS Code, and Discord. It connects via the Chrome DevTools Protocol to execute accessibility-tree based element interaction within these environments.

What is the best way to run automated web testing and scraping in cloud environments?

Automated web testing and scraping in cloud environments is supported through Vercel Sandbox microVM execution and AWS Bedrock AgentCore cloud browsers. This allows agents to run tasks remotely without local Chrome dependencies.

Do I need Chrome CDP access to perform web scraping with AI agents?

Yes, Chrome or Chromium CDP access is required for web scraping with AI agents. The environment must have the agent-browser CLI installed globally to perform accessibility-tree based element interaction and session state persistence.

How does automated QA testing work for web applications using AI workflows?

Automated QA testing for web applications uses AI workflows to navigate sites, submit forms, and capture screenshots programmatically. It leverages the Chrome DevTools Protocol to interact with elements via the accessibility tree.