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
CS Skills 是陈硕在真实项目中沉淀的一组 Codex AI Agent 工作流。
一个跨窗口、跨模型、跨设备、跨语言的开源 AI 上下文交接工具，基于开放的 Agent Skills 协议；实际验证范围以公开兼容矩阵为准。
The financial data layer for AI agents. Open-source alternative to FactSet / Daloopa / S&P Global for AI agents. 165+ US equities with full SEC filing history. 31 Claude-type skills. 20+ MCP tools.
An unofficial agent skill for drafting, revising, and auditing clear technical and product documentation.
Make your agentic workflows durable with embeddable primitives that compose with your existing infra. No server, no dedicated runtime, no new infra.
The core philosophy of fp-pack is simple: It's a pipe-first toolkit for everyday code—approachable, zero-deps, and tree-shakeable.
论文去 AI 味 · AI 痕迹检测 · 学术润色｜面向华为杯中国研究生数学建模竞赛的 Codex Skill，支持逐句诊断、去模板化改写、图表优化、规则核验与提交审计，保留研究事实与引文。
Local ears and mouth for your LLM — offline, private, safe, free & open source. Voice-enable any local LLM stack: Claude Code, OpenCode, Hermes, Llama.cpp, vLLM, Ollama and more.
Extract Markdown, JSON (with bounding boxes), and HTML from any born-digital PDF — deterministically, in milliseconds, on CPU.
精选的 Clawdbot 技能合集 - 565+ 个社区构建的技能，分类整理便于发现 | A curated collection of 565+ Clawdbot skills
审查论文对应的代码实现是否完整合法的skill
(build 20260317.0002) — 面向所有支持 Skill 的 Agent 平台，提供六维深度安全分析和 S+ ~ D 等级评估