chrome-cdp

Control a local headful Chrome browser via the DevTools Protocol.

6|Updated Feb 25, 2026
One-click install
npx skills add https://github.com/archibate/archibate-skills --skill chrome-cdp-archibate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: chrome-cdp
Source: https://github.com/archibate/archibate-skills/tree/main/skills/chrome-cdp
Command: npx skills add https://github.com/archibate/archibate-skills --skill chrome-cdp-archibate

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Enables safe, user-approved inspection and automation of a local headful Chrome (or Chromium-family) browser by speaking directly to the DevTools Protocol, avoiding heavyweight tooling and enabling fast interactions across many open tabs.

Core Features & Use Cases

  • List and target pages: discover open page targets and resolve unique target prefixes for precise operations.
  • Interact and automate: navigate pages, evaluate JavaScript, click elements, type text, perform raw CDP commands, and capture viewport screenshots with DPR-aware coordinate mapping.
  • Per-tab daemons and IPC: runs lightweight per-tab daemons with a newline-delimited JSON socket protocol for scripting and long-lived sessions; useful for debugging, accessibility snapshots, scraping dynamic content, and reproducible test interactions.

Quick Start

Use the chrome-cdp skill to list open tabs, attach to a target with your approval, and capture a viewport screenshot of the active page.

Frequently Asked Questions about chrome-cdp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate a local headful Chrome browser using the DevTools Protocol?

You can automate local headful Chrome by speaking directly to the DevTools Protocol. The chrome-cdp skill enables navigation, element interaction, and viewport screenshots across open tabs.

Can I capture DPR-aware screenshots from open Chrome tabs?

Yes, you can capture viewport screenshots with DPR-aware coordinate mapping. This ensures accurate high-resolution captures of active pages when automating a local Chrome browser.

What do I need to run Chrome DevTools Protocol automation locally?

You need remote debugging enabled in a desktop Chromium-family browser and Node.js 22+. You must also grant explicit user permission for headful access to run the automation daemons.

How does browser automation handle multiple open pages?

The automation uses per-tab daemons with a newline-delimited JSON socket protocol. This allows long-lived sessions to discover open page targets and resolve unique target prefixes for precise operations.

Can I execute raw Chrome DevTools Protocol commands for accessibility snapshots?

Yes, the skill supports raw CDP command passthrough. This allows you to evaluate JavaScript, take accessibility snapshots, and interact with dynamic content directly.

What is the best way to inspect local Chrome tabs without heavyweight tooling?

The best way to inspect local Chrome tabs without heavyweight tooling is using the chrome-cdp skill. It applies directly to desktop Chromium-family browsers for fast debugging and reproducible test interactions.