use-my-browser

Community

Extract real-time evidence from a live browser.

Authorxixu-me
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It addresses situations where agents need evidence from the user's current browser session—such as logged‑in dashboards, local apps, dynamic pages, or DevTools contexts—rather than relying on static retrieval.

Core Features & Use Cases

  • Goal‑first routing: classifies tasks as static‑capable or browser‑required and selects the cheapest path that still yields the required evidence.
  • Live‑browser session reuse: attaches to the user's existing Chrome DevTools MCP session, preserving login state and UI context.
  • DevTools handoff & deep‑DOM handling: can continue from a selected element or network request, inspect iframes, Shadow DOM, lazy‑loaded content, and media.
  • Safety & recovery: enforces confirmation discipline for control‑plane actions and provides structured recovery loops for anti‑automation friction, stale uids, and unexpected navigation.

Quick Start

Ask the agent to use the browser skill to verify the visible state of a logged‑in dashboard without requiring a new sign‑in.

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: use-my-browser
Download link: https://github.com/xixu-me/skills/archive/main.zip#use-my-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 471,000+ vetted skills library on demand.