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
Diagnose and Fix CUDA / GPU environments compatibility issues locally, in Docker, and CI/CD. CLI + MCP server available.
Zero-configuration MCP server that unifies multiple AI coding assistants (Codex, Claude Code, Cursor, Gemini) through intelligent auto-discovery and standardized interface
Memory management MCP server for AI agents using Neo4j knowledge graphs
WhatsApp MCP server - Connect Claude to WhatsApp for reading and sending messages
An MCP Server for audio transcription using OpenAI
Give AI agents the complete Godot development loop: discover, build, play, observe, debug, fix, and verify from a CLI or MCP client.
Gemini, Codex, Claude, and OpenCode all in a single MCP tool for use by any coding agent.
A Model Context Protocol (MCP) server for interacting with the Godot game engine.
Enable AI to debug PHP with Xdebug
MCP server enabling AI assistants to read and write GnuCash accounting data
Your Obsidian vault, exposed to Claude and any MCP client. Runs inside Obsidian, on-device semantic search, no cloud round-trip, no binary to download.
A MCP server that is a locally running knowledge base with a hybrid vector and graph RAG engine using LightRAG
Agent Skills
你現在是 lo2cin4bt 的專案經理（Project Manager，PM）。請檢查本機環境、初始化內建策略示範，並幫我執行 QQQ 日線簡單移動平均線（Simple Moving Average，SMA）穿越回測。整個流程只做本機研究，不要實盤交易或下單。
A Next.js + TypeScript + vanilla-CSS component library from the Internet Development Studio Company. It's a precise wireframe system — every pixel, token, and transition is deliberate — and it's...
把"做小红书虚拟资料"从一份教程，变成一套可复用的 AI 工作流 Skill 选品 → 对标 → 制作 → 上架 → 内容 → 复盘 ｜ 全流程模板 · 公式 · 检查清单 ｜ 守住版权合规红线
AI agents Rules / Skills from Programming Books v0.5
Benjamin-Plus: a measured token-efficiency skill for coding agents (−17.9% cost median, quality unchanged). Inject it, don't install it.
A composable dev process for agentic coding harnesses, packaged as modular skills. Turbo has sibling editions for Claude Code and Codex.
High-performance personal AI assistant in C++17
A practical library of , , and designed specifically for QA Automation Engineers, focusing on production-oriented solutions.
Local-first Research OS for papers, workflows, experiments, channels, and automation.
Built from practice, not theory — calibrated against real deals including vLLM/Inferact ($150M @ $800M) and Hugging Face ($235M @ $4.5B).
A high-performance, enterprise-grade Next.js 16 application for mission-focused non-profit organizations. Built for high impact teams.
This is an project. These templates are designed to run on the OpenClaw platform — they use OpenClaw's agent system, workspace structure, session management, sessions_send for bot-to-bot...