agent-browser

Automate Chrome/Chromium browser actions via a command-line interface.

2|Updated Jun 29, 2026
One-click install
npx skills add https://github.com/Axel-DaMage/opencode-config --skill agent-browser-axel-damage
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Axel-DaMage/opencode-config/tree/main/skills/agent-browser
Command: npx skills add https://github.com/Axel-DaMage/opencode-config --skill agent-browser-axel-damage

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agent-browser, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines browser automation tasks in Chrome/Chromium, allowing users to interact with web pages programmatically without the need for complex scripting.

Core Features & Use Cases

  • Browser Navigation: Open websites, click buttons, fill forms, take screenshots, and scrape data.
  • Scripting Capabilities: Execute Bash scripts with agent-browser for additional functionality.
  • Use Case: Automate login processes, fill out complex web forms, and capture screenshots for documentation or analysis.

Quick Start

Use the agent-browser skill to navigate to "https://example.com" and click the "Submit" button.

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 in Chrome without writing complex scripts?

Automate web scraping by using a simple command-line interface to interact with Chrome/Chromium pages programmatically, executing Bash scripts for repetitive data extraction without complex scripting.

What do I need to set up before automating browser actions with a CLI?

Browser automation requires the agent-browser CLI tool installed and Chrome/Chromium running with remote debugging enabled to allow programmatic interaction with open web pages.

Can I automate form submission and button clicks on web pages programmatically?

Yes, form submission and button clicks are fully supported, allowing you to navigate to target websites, fill out complex web forms, and submit them automatically via command-line scripts.

How does command-line browser automation handle screenshots for documentation?

Command-line browser automation captures screenshots directly from the active Chrome/Chromium session, providing image outputs for documentation and analysis of the navigated web pages.

What are the limitations of using Bash scripts for browser automation?

The primary limitation is its dependency on an active browser session; remote debugging must be enabled in Chrome/Chromium beforehand, and it is designed for repetitive tasks rather than headless background processing.