chrome-browser

Community

Automate browser tasks via CDP-enabled Chrome.

Authoraj47
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill enables automated browser tasks by connecting to a logged-in Chrome session via the Chrome DevTools Protocol (CDP). It lets you perform web interactions without manually operating the browser.

Core Features & Use Cases

  • Connect to a running Chrome instance on port 9222 using the agent-browser CLI and perform navigation, form filling, button clicks, and data extraction.
  • Snapshot-interact workflow: capture interactive element refs, perform actions, then re-snapshot after DOM changes to keep refs valid.
  • Debug and setup guidance: utilize a saved Chrome profile to preserve logins and use the dedicated debugging workflow for browser automation.

Quick Start

Open a URL in your logged-in Chrome session via agent-browser --cdp 9222 and automate the desired interactions.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: chrome-browser
Download link: https://github.com/aj47/agent-skills/archive/main.zip#chrome-browser

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.