Cursor 安装指南
常与开发类 MCP Server 搭配使用的 AI 代码编辑器。
MCP Servers
A secure, remote-accessible MCP server that gives LLMs read/write access to your Obsidian vault from anywhere -- your desktop, your phone, a hotel Wi-Fi network.
A library built on top of the MCP TypeScript SDK that makes it easier to implement MCP with auth into your MCP client and/or server.
Making AI coding assistants experts at Swift and iOS development.
This is an MCP server that connects Reaper projects to an MCP client like Claude Desktop, enabling you to ask questions about your projects and get comprehensive audio analysis for mixing feedback.
Professional Serial Port Debugging Assistant with Modbus, PLC, CAN, I2C/SPI support and MCP server
移动端 AI 自动化测试平台 —— MCP 工具 + AI Agent + 可视化操控台
This repo provides a reference implementation for creating a remote MCP server that supports the Streamable HTTP & SSE Transports, authorized with OAuth based on the MCP specification.
Desktop extension (.mcpb) for Claude Desktop. Single-click install via Settings → Extensions.
A Stdio MCP server which proxies an SSE MCP server.
Generic markdown vault MCP with hybrid search
a lib to build MCP clients and MCP servers in Clojure(script)
Home of — the slash commands and MCP connection that let an agent generate images, video, audio, and 3D, search models and nodes, and run ComfyUI workflows through Comfy Cloud.
Agent Skills
It turns one coding agent into a structured engineering team: PM, Architect, UI Designer, Tech Lead, Scrum Master, Frontend, Backend, QA, and DevOps.
Documentation compiler for humans and machines. One Markdown source to website, search, AI context, and knowledge formats together.
A curated list for awesome cloud native tools, software and tutorials.
Office Agents is a monorepo of Microsoft Office Add-ins with integrated AI chat panels. Each add-in connects to major LLM providers using your own credentials (BYOK) and can read/write documents...
⛏️ Turning data into a visual language for better thinking with Skills.
Let AI agents use your browser without interrupting your work.
4 risk tiers · 11 damage control procedures · 11 mission templates · 7 crew roles · 16 standing orders
Stop trusting Claude's first answer. Run any decision through 5 AI advisors who argue, peer-review each other anonymously, and hand you a verdict you can actually trust.
is a graph-centric framework for orchestrating Multi-Agent Systems with :
亲爱的开发者们，这是一个经过整理和中文化的 Anthropic Skills 仓库。无论你是想快速了解 Claude 技能体系的最佳实践，还是需要直接上手 Word/PDF/PPTX/XLSX 处理脚本，这份中文版都能帮你省去大量摸索时间。
给 Agent 一个链接，它会先选对读取通道，再把完整原文交给后续的总结、写作、翻译或分析任务。
一套中文去 AI 味提示词，打包成 SKILL 格式，适用于 Claude Code、Cursor、Windsurf 等支持 SKILL 调用的工具。核心做的事情就两件：把 AI 生成的中文改得不像 AI 写的，以及复现一个真实作者的写作风格。