control-chrome

Automate Chrome browser navigation, interaction, and inspection through a Node REPL runtime.

Updated Jul 31, 2026
One-click install
npx skills add https://github.com/AarnavBaddam/skills --skill control-chrome-aarnavbaddam
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: control-chrome
Source: https://github.com/AarnavBaddam/skills/tree/main/control-chrome
Command: npx skills add https://github.com/AarnavBaddam/skills --skill control-chrome-aarnavbaddam

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? Automating tasks that depend on existing Chrome state—open tabs, logged-in sessions, or installed extensions—requires direct browser control, which generic APIs and connectors cannot provide. ## Core Features & Use Cases - Browser Selection & Binding: Select the in-app browser or Chrome based on explicit user requests, target URLs, or runtime defaults, with persistent bindings reused across turns. - Page Automation: Navigate pages, click elements, type input, take screenshots, and read visible page state through the browser-client runtime. - Troubleshooting Guidance: Built-in documentation topics for bootstrap failures and Chrome extension setup or communication issues. - Use Case: A user asks to fill out a form on a site where they are already logged in; the Skill connects to their Chrome session, navigates to the page, and completes the form using the existing authenticated state. ## Quick Start Connect to my Chrome browser and open the current tab to check whether I am signed in to my account.

Frequently Asked Questions about control-chrome

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

FAQPage Schema
How do I automate Chrome browser tasks with an AI agent?

Use the browser-client module loaded through the Node REPL js tool to initialize a browser runtime, then select a browser binding and control tabs for navigation, clicking, typing, and screenshots. The runtime reuses existing Chrome sessions and state.

When should I use browser automation instead of an API or connector?

Use browser automation only when no purpose-built connector, API, or CLI can handle the operation, or when the task requires existing Chrome state like logged-in sessions or extensions. Always query available tools first before initializing the browser.

Can browser automation access my logged-in Chrome sessions?

Yes, the Chrome browser binding operates on the user's actual Chrome instance, preserving logged-in sessions and open tabs. It does not inspect cookies, local storage, passwords, or session stores during discovery.

Why does Chrome browser setup fail or lose connection?

Failures typically come from Chrome extension setup, installation, or communication issues. Read the chrome-troubleshooting documentation topic before retrying, and use bootstrap-troubleshooting when setup succeeds but browser discovery or selection fails.

What are the limitations of Chrome browser automation?

Browser automation cannot bypass authentication walls by substituting other sites or search engines, and it should not replace dedicated connectors when those handle the task. Tab bindings can go stale and must be re-obtained from the existing browser binding.