skills.rest
ethan-rio
ethan-rioCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automate web and Electron desktop app interactions via Chrome DevTools Protocol.

Updated May 5, 2026
Search Tags:#browser automation#web scraping#web interaction#agent workflows#qa testing#slack automation#electron apps
One-click install
npx skills add https://github.com/ethan-rio/skills --skill agent-browser-ethan-rio
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/ethan-rio/skills/tree/main/skills/productivity/agent-browser
Command: npx skills add https://github.com/ethan-rio/skills --skill agent-browser-ethan-rio

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually navigating websites, filling forms, scraping data, testing web apps, and automating desktop applications like Slack or VS Code is time-consuming and error-prone for both users and AI agents. This Skill eliminates that friction by providing a reliable, programmatic browser automation tool built specifically for agent workflows.

Core Features & Use Cases

  • Cross-platform browser automation: Interact with any web page (navigate, fill forms, click elements, take screenshots, extract data, run tests) and automate Electron desktop apps including VS Code, Slack, Discord, Figma, Notion, and Spotify.
  • Specialized workflow support: Built-in capabilities for Slack workspace automation (checking unreads, sending messages, searching conversations), exploratory testing/QA/bug hunts, and cloud browser execution via Vercel Sandbox microVMs or AWS Bedrock AgentCore.
  • Reliable agent-friendly design: Uses Chrome DevTools Protocol with accessibility-tree snapshots and unique element references for consistent, error-resistant interactions, plus session persistence, authentication vaults, and video recording for audit trails.

Quick Start

Use the agent-browser skill to log in to your Slack workspace, check your unread messages, and send a summary of urgent items to your team channel.

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 for AI agents?▼

Automate web scraping and form filling for AI agents by using Chrome DevTools Protocol integration with accessibility-tree snapshots to programmatically navigate pages, click elements, and extract data reliably.

Can I automate Electron desktop apps like Slack and VS Code with browser automation?▼

Yes, you can automate Electron desktop apps like Slack, VS Code, Discord, and Notion. The tool uses Chrome DevTools Protocol integration to interact with desktop application interfaces programmatically.

What's the best way to run exploratory QA testing and bug hunts in a cloud browser?▼

Run exploratory QA testing and bug hunts in a cloud browser using Vercel Sandbox microVMs or AWS Bedrock AgentCore environments, capturing video recordings and accessibility-tree snapshots for reliable, auditable test trails.

Does browser automation work with Slack workspace operations like checking unread messages?▼

Browser automation supports Slack workspace operations including checking unread messages, sending messages, and searching conversations. It maintains session persistence and authentication vaults for continuous authenticated access.

How does element reference mapping prevent errors during web interaction automation?▼

Element reference mapping prevents errors during web interaction automation by assigning unique references to accessibility-tree snapshot nodes, ensuring agents target the correct elements consistently across dynamic page updates.

Do I need a Rust CLI to use browser automation for agent workflows?▼

Yes, you need the agent-browser Rust CLI to enable Chrome or Chromium CDP integration. It generates the accessibility-tree snapshots and manages session and authentication state persistence required for reliable agent workflows.

Related Skills

Explore More Software Engineering Skills→
remcostoetenremcostoeten
14

agent-browser

Automate web and desktop application interactions through a native Chrome/Chromium CDP interface.

Community
Advanced
archibatearchibate
6

slack

Automate Slack web workspace interactions to read messages and extract channel metadata.

Community
Intermediate
tsaoltsaol
66

browser-use-agentcore

Automate cloud-based browser testing and screenshot capture with AWS Bedrock AgentCore Browser.

Community
Advanced
MarcoDavaMarcoDava
1

browser

Automate browser navigation, clicking, form filling, and screenshots using AI-optimized snapshots.

Community
Intermediate