dcc123456

Browser Copilot — AI skill for Claude Code

AI community

AI side-panel assistant for Chrome.

How to install Browser Copilot

This entry records only its repository, not the path inside it, so there is no exact command to give. Open dcc123456/browser-copilot and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Browser Copilot does

AI side-panel assistant for Chrome. Reads the active page and acts on it with your approval — click, type, switch tabs, fill forms. Multi-LLM, reusable Skills, recordable workflows, MCP bridge to Claude Code / Codex / Trae, optional Node/Playwright runner.

Alternatives in AI

  • Internal Safety Collapse — We built an adversarial codespace setup 1.2k ★
  • Minuet Ai.nvim — Code completion as-you-type from popular LLMs including OpenAI, Gemini, Claude, Ollama 1.1k ★
  • AI Investigator — An automated AI system (Python framework) designed to analyze any type of website content and generate structu 733 ★

README

Browser Copilot

[![Version](https://img.shields.io/github/v/release/dcc123456/browser-copilot?label=version&color=5b8cff)](https://github.com/dcc123456/browser-copilot/releases) [![Chrome](https://img.shields.io/badge/Chrome-116%2B-4285f4?logo=googlechrome&logoColor=white)](https://developer.chrome.com/docs/extensions/develop) [![License](https://img.shields.io/badge/license-PolyForm--Noncommercial-6e40c9)](./LICENSE) [![CI](https://img.shields.io/github/actions/workflow/status/dcc123456/browser-copilot/ci.yml?label=ci)](https://github.com/dcc123456/browser-copilot/actions)

**English** · [简体中文](README.zh-CN.md)

Your AI assistant that actually _uses_ the web for you. Open the side panel, ask in plain language, and Browser Copilot reads the page you're on and takes action — clicking buttons, filling forms, scrolling, switching tabs, walking through a whole checkout or setup flow — while you watch or stay hands-off.

  • 🧠 Works with the model you already use. Any OpenAI-compatible endpoint: DeepSeek, 火山方舟 Ark, OpenAI, OpenRouter, Moonshot, DashScope, SiliconFlow, or a local Ollama/LM Studio. Bring your own key.
  • 🎚️ You choose how autonomous it is. Four modes from plain chat to full auto; semi-auto shows every click for your approval first.
  • 🧩 Skills turn repeatable know-how (review checklists, style guides, extraction formats) into one-tap instructions the model must follow.
  • 🎬 Workflows run whole procedures on their own. Record yourself doing a task once, or assemble it on a visual canvas from 56 block types — clicking, filling, loops, condition branches, even an AI-agent step — then launch it by hand, on a schedule, at startup, with a keyboard shortcut, from a context menu, or when a matching page is opened.
  • Runs on a schedule while you sleep. Set recurring tasks — every few minutes, daily, or on weekdays — to run an unattended prompt or summarize your GitHub review queue, with a full run history.
  • 💬 **Picks up