agent-browser

Automate web and Electron app interactions via Chrome/Chromium CDP.

1|Updated Jan 25, 2026
One-click install
npx skills add https://github.com/a35506322/Lab.Todo --skill agent-browser-a35506322
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/a35506322/Lab.Todo/tree/main/.cursor/skills/agent-browser
Command: npx skills add https://github.com/a35506322/Lab.Todo --skill agent-browser-a35506322

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manual browser automation is slow, repetitive, and prone to human error for tasks like filling out forms, scraping web data, testing web applications, or automating repetitive actions in desktop apps like Slack and VS Code. This skill removes that overhead by providing a fast, reliable CLI tool for programmatic browser interaction.

Core Features & Use Cases

  • Web browser automation: Navigate pages, fill forms, click buttons, take screenshots, extract data, and test web apps using Chrome/Chromium via CDP with accessibility-tree snapshots for reliable element interaction.
  • Electron desktop app automation: Automate tasks in popular Electron apps including VS Code, Slack, Discord, Figma, Notion, and Spotify.
  • Specialized workflows: Built-in support for Slack workspace automation, exploratory testing and bug hunts, Vercel Sandbox microVM execution, and AWS Bedrock AgentCore cloud browser integration.
  • Use Case: A developer can use this skill to automatically test a new web app's end-to-end user flow, scrape product pricing data from an e-commerce site, or automate sending daily standup updates to a team Slack channel without manual effort.

Quick Start

Use the agent-browser skill to navigate to the specified e-commerce product page, extract the price and availability information for the listed item, and save the data to a local CSV file.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate web scraping and form filling without manual effort?

Web scraping and form filling are automated by programmatically interacting with web pages via Chrome/Chromium CDP, using accessibility-tree snapshots for reliable element selection and data extraction.

Can I automate tasks in Electron desktop apps like Slack and VS Code?

Electron desktop apps like Slack and VS Code are supported for task automation, enabling programmatic interaction and workflow execution within these applications using Chrome/Chromium CDP.

What do I need to run browser automation tasks in a cloud environment?

Cloud browser execution requires the agent-browser CLI installed globally alongside Chrome/Chromium dependencies, supporting specialized workflows in Vercel Sandbox microVMs and AWS Bedrock AgentCore environments.

How does browser automation find and interact with web page elements?

Browser automation locates web page elements using accessibility-tree based references, capturing snapshots to ensure reliable interaction when navigating pages, clicking buttons, or taking screenshots.

Does this tool support end-to-end web application testing workflows?

End-to-end web application testing is supported, allowing developers to automate user flows, conduct exploratory testing, perform bug hunts, and capture screenshots programmatically.

What are the limitations of using CDP for desktop app automation?

Desktop app automation via CDP is limited to Electron-based applications like Figma, Notion, and Spotify, requiring specific Chrome/Chromium dependencies to be present for accessibility-tree interaction.