agent-browser

Control Chrome/Chromium instances for browser automation via CDP.

Updated Mar 24, 2023
One-click install
npx skills add https://github.com/j4hr3n/dotfiles --skill agent-browser-j4hr3n
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/j4hr3n/dotfiles/tree/main/configs/claude-code/skills/agent-browser
Command: npx skills add https://github.com/j4hr3n/dotfiles --skill agent-browser-j4hr3n

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AI agents often need to interact with dynamic web pages, sign-in flows, and multi-step forms, but doing this manually is slow and error-prone; this skill provides a programmable browser automation interface to handle navigation, elements, authentication, and data extraction.

Core Features & Use Cases

  • CLI-driven browser control with commands to open pages, snapshot elements, fill forms, click controls, and manage tabs.
  • Supports authenticated browsing, session persistence, proxies, iframe handling, and network inspection for robust automation pipelines.
  • Use cases include automated data extraction, form submission, end-to-end testing, and reproducible web scraping across multiple sessions.

Quick Start

Use this skill to orchestrate a browser session and learn page structure by opening a URL and taking an initial snapshot.

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 with AI agents for web navigation and form filling?

Browser automation for AI agents is achieved by controlling a Chrome or Chromium instance, enabling programmatic web navigation, form filling, and element interaction. This skill provides a CLI-driven interface to open pages, take snapshots, and click controls.

What is the best way to handle authenticated browsing and session persistence in web scraping?

Authenticated browsing and session persistence in web scraping are managed through a CLI that supports session management, proxies, and CDP connections. This allows multi-session workflows to maintain login states across automated browser tasks.

Does browser automation work with iframes and network inspection for dynamic web pages?

Browser automation does work with iframes and network inspection for dynamic web pages. The skill handles iframe interactions and provides network inspection capabilities to support robust automation pipelines on complex page structures.

How do I extract page elements and learn web page structure for automated data extraction?

To extract page elements and learn web page structure for automated data extraction, you open a URL and take an initial snapshot using the CLI. This snapshot captures the page structure for AI agents to interact with targeted elements.

Can I run end-to-end testing and multi-session workflows using a Chrome instance?

You can run end-to-end testing and multi-session workflows using a controlled Chrome instance. The skill supports managing multiple tabs, applying proxies, and handling authentication to execute reproducible testing across sessions.

What are the limitations of using CLI-driven browser control for web scraping?

Limitations of CLI-driven browser control for web scraping involve dependencies on a controllable Chrome or Chromium instance and potential restrictions when handling highly dynamic pages without proper CDP connections or proxy configurations.