Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers

Real reap --agent output, run against a generated sample stack ( hero-fixture.sh ) — not anyone's install. The numbers further down are measured on mine.

⚠️ :此项目完全是 vibe coding 产物,代码由 AI 生成,未经严格审查。使用风险自己承担。

ChatCrystal is a local-first AI PKM app for developers who solve real problems with Claude Code, Cursor, Codex CLI, Trae, and GitHub Copilot.

Open-source NURBS surface modeller — a Rhino-style freeform modeller on the OpenCASCADE kernel, with AI-native MCP integration

移动端 AI 自动化测试平台 —— MCP 工具 + AI Agent + 可视化操控台

🔥 MCP Mastery: Build AI Apps with Claude, LangChain and Ollama

A modular MCP server providing AI-driven vulnerability management skills, including severity classification and automated insights.

Unified native desktop UI for Claude Code, Gemini CLI, Hermes, Crush, Codex, and Cursor — multi-agent, MCP-native, written in Rust + GPUI.

Drop a .pcap file, ask questions in plain English — get answers backed by real tshark data.

ChiKen is your private, AI-powered research assistant that transforms your Zotero library into an interactive knowledge base.

AI-powered penetration testing MCP server

The MCP ecosystem has grown to 10,000+ servers, but discovering and installing them remains painful. Existing directories — Glama, PulseMCP, mcp.so — are all closed source.
Agent Skills

📈 SEO & Content Marketing skill suite derived from vincenthopf/My-Claude-Code.

마크다운 노트를 RDF/TTL 지식 그래프로 변환 - SPARQL 질의로 시맨틱 검색

API rate-limit docs: quotas, headers, 429, backoff — predictable tone.

Generative UI for LLMs using Markdoc {% %} tag syntax

解析tmdb hosts,防止dns污染

Superpowers workflow skill pack adapted for Hermes Agent and ChatGPT

Agentic loop image generation without diffusion or autoregressive image models. Coding agents draw in p5.

雅思自学 skills,用于搭配 ClaudeCode 自学雅思,功能丰富好用

Efficient multi-strategy Zotero search using code execution pattern

AWSでAIエージェントのWebアプリを作るためのスキル集

VLA Expert Skill 一键让你的 AI 编程助手变成 VLA 领域专家。它解决两件事:1. 注入 332+ 篇论文的压缩知识——不是摘要,是拆解后的工程细节、架构选择、训练配方。2. 内置对抗性思考纪律——每个判断都经过双向取证、来源分级、可证伪检验,不让 AI 输出正确的废话。每天早上自动更新。

Deep Skill Finder – Find the right Skill for every Agent task