agent-browser

Automate web browser tasks via Chrome/Chromium CDP or Lightpanda.

1|Updated Apr 4, 2026
One-click install
npx skills add https://github.com/ybbms777/compound-engineering --skill agent-browser-ybbms777
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/ybbms777/compound-engineering/tree/main/skills/agent-browser
Command: npx skills add https://github.com/ybbms777/compound-engineering --skill agent-browser-ybbms777

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill eliminates the need for manual browser interaction when AI agents need to navigate websites, fill forms, extract data, or test web applications, removing repetitive human effort from web automation tasks.

Core Features & Use Cases

  • Full Browser Automation: Navigate pages, fill forms, click buttons, take screenshots, and extract data from any website using Chrome/Chromium or the lightweight Lightpanda browser.
  • Flexible Authentication Handling: Supports persistent sessions, state saving/loading, OAuth, 2FA, and encrypted credential vaults for accessing protected web apps without repeated logins.
  • Use Case: For example, use this Skill to automatically log into a SaaS dashboard, scrape product pricing data from multiple pages, and save annotated screenshots of the results for reporting, all without manual input.

Quick Start

Use the agent-browser skill to log into the target web application, extract the required data from the dashboard, and save the extracted content to a local file for analysis.

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 browser interactions for AI agents without manual intervention?

Automating web browser interactions for AI agents requires a tool that supports end-to-end navigation, form submission, and data scraping via Chrome/Chromium or Lightpanda. This enables agents to execute website tasks autonomously, removing repetitive human effort.

Can I manage authenticated sessions and 2FA logins during web scraping tasks?

Managing authenticated sessions and 2FA logins during web scraping is supported through persistent session states, encrypted credential vaults, and OAuth integration. This allows agents to access protected web applications and maintain authenticated states across multiple interactions.

Does browser automation support headless environments like Lightpanda for automated web testing?

Headless browser automation for automated web testing supports both Chrome/Chromium via CDP and the Lightpanda browser. This allows AI agents to execute visual regression testing and application testing tasks across desktop and mobile environments.

How do I extract data and save session states from restricted or geo-located web pages?

Extracting data and saving session states from restricted or geo-located web pages is handled through configurable proxy support and session state persistence. This enables AI agents to bypass geographic restrictions and maintain browsing contexts for data scraping.

What do I need to set up end-to-end web form filling and data extraction for AI workflows?

Setting up end-to-end web form filling and data extraction requires installing the agent-browser CLI tool globally. Once installed, AI agents can navigate pages, click buttons, take screenshots, and extract data from any target website autonomously.