chrome-cdp-skill
Allow AI agents to access and operate your real-time Chrome session.
- Type
- Agent Skill
- Open source
- Yes
- GitHub Stars
- ★ 3.1k
- Source
- skill-github
- Repository
- github.com/pasky/chrome-cdp-skill
Overview
chrome-cdp-skill enables AI agents to access and control your currently open Chrome tabs without needing to re-login or launch a new browser instance. It connects directly to your running Chrome session, allowing the AI to read logged-in pages, interact with active tabs, and view actual page states. Ideal for automation scenarios within existing workflows.
Capabilities
- ▪Read logged-in pages
- ▪Interact with active tabs
- ▪View actual page state
- ▪Take screenshots
- ▪Execute JavaScript code
- ▪Click elements
Use cases
Setup
pi install git:github.com/pasky/chrome-cdp-skill@v1.0.1 or clone the `skills/chrome-cdp/` directory and enable remote debugging.
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How to enable remote debugging?
Go to chrome://inspect/#remote-debugging and toggle the switch.
Which browsers are supported?
Supports Chrome, Chromium, Brave, Edge, and Vivaldi.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.