skills.rest
ckorhonen
ckorhonenCOMMUNITY
Explore all skills by this author →
Website𝕏@ckorhonenGitHub

agent-browser

Automate headless browser interactions with a Rust-based CLI and JSON output.

12|Updated Dec 13, 2025
Search Tags:#automation#testing#cli#scraping#browser#headless#element-refs
One-click install
npx skills add https://github.com/ckorhonen/claude-skills --skill agent-browser-ckorhonen
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/ckorhonen/claude-skills/tree/main/skills/agent-browser
Command: npx skills add https://github.com/ckorhonen/claude-skills --skill agent-browser-ckorhonen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automate headless browser tasks for AI-driven workflows, removing manual, repetitive interactions and enabling reliable automation across web pages.

Core Features & Use Cases

  • Fast Rust-based CLI with a Node.js fallback for broad compatibility
  • Stable element references (@e1, @e2) to anchor interactions and improve reliability
  • Session isolation for parallel browser instances and multi-task automation
  • JSON output for easy machine parsing and scripting
  • Accessibility-tree snapshots for element discovery and debugging
  • CDP connectivity to attach to existing browser sessions

Quick Start

Open a page and snapshot interactive elements to begin automating with AI agents.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate headless browser tasks for AI workflows?▼

You can automate headless browser tasks using a Rust-based CLI with a Node.js fallback, enabling reliable web scraping, form submission, and automated testing. It provides JSON output for easy machine parsing and scripting.

How do stable element references improve web scraping reliability?▼

Stable element references like @e1 and @e2 anchor interactions to specific page elements, improving reliability during web scraping and form submission. This prevents automation scripts from breaking when page layouts shift.

Can I run parallel headless browser instances with session isolation?▼

Yes, session isolation supports parallel browser instances and multi-task automation. This allows you to run multiple independent browsing scenarios simultaneously without sessions interfering with each other.

Does this browser automation tool support CDP connectivity?▼

Yes, it supports CDP connectivity to attach to existing browser sessions. This allows you to connect your automation scripts to browser instances you already have running, rather than always starting new ones.

Do I need Rust installed to run this headless browser CLI?▼

No, Rust is not strictly required because there is an optional Node.js fallback for broad compatibility. The Rust-based core provides faster performance, but the Node.js fallback ensures you can run it without a Rust environment.

What is the best way to discover interactive elements during automated testing?▼

The best way to discover interactive elements is by taking accessibility-tree snapshots. These snapshots provide a structured view of the page, allowing you to identify elements and debug your automation workflows effectively.

Related Skills

Explore More Software Engineering Skills→
marktantongcomarktantongco
2

Agent Browser

Automate browser navigation and DOM interactions via a headless CLI.

Community
Advanced
ouakarouakar

web-scraper

Extract structured data from websites with sanitized Markdown output.

Community
Advanced
JoeyJoziahJoeyJoziah

browser

Automate web browser interactions using accessibility-tree snapshots and element references.

Community
Advanced
InternLMInternLM
501

agent-browser

Automate headless browser navigation, interaction, and data extraction with Puppeteer.

Official
Intermediate