Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Turn scattered notes, documents, and transcripts into a searchable, queryable personal Wiki — powered by LLM-driven knowledge compilation.
AI-assisted TradingView chart analysis — connect Claude Code to your TradingView Desktop for personal workflow automation
Drop‑in Express middleware and helpers to add secure auth to your Model Context Protocol (MCP) server with Descope. Ship an authenticated /mcp endpoint and register tools in minutes.
Looking for the Python version? Check out Saiku.py.
This is a simple MCP (Model Context Protocol) server that connects to the PokéAPI and exposes tools that an LLM can use to fetch Pokémon data, list popular Pokémon, and build a tournament squad.
本地 AI Agent 的统一管理中心。 添加 Agent 后，用户可在这里实现： - 一键启动 / 停止，实时查看日志 - 内嵌 Web UI 与交互式终端 - 用自然语言指挥所有 Agent - 一键生成临时公网分享链接
A Model Context Protocol (MCP) server that gives LLMs access to information about a candidate.
An OAuth 2.1 Authorization Server that adds authentication to any MCP (Model Context Protocol) server without code modification.
mcp4k is a compiler-driven framework for building both clients and servers using the Model Context Protocol (MCP) in Kotlin.
Run Classic ASP on Linux, Windows, and macOS natively with extreme performance.
A comprehensive system for searching and analyzing German legal texts using vector embeddings and semantic search, consisting of:
A Model Context Protocol (MCP) server for Windows desktop automation using AutoIt.
Agent Skills
AI assistant for Obsidian with , , and powered by Google Gemini.
基于 Claude Code Agent Skills 的 AI 提示词工程系统 - 10个场景化专家，自动路由，精准生成优秀提示词 ## 项目简介 这是一个基于 Claude Code Agent Skills 技术的智能提示词生成系统。通过自然语言请求，系统会自动路由到对应的专业 Skill，帮助用户写出高质量的 AI 提示词。
基于 LangGraph 和 DeepAgents 框架的智能体 Skills 能力演示项目。
基于 GJB 438C-2021 [5.10] 标准模板的 SRS 文档自动生成
Generate and review MiniMax H3 video prompts from user goals and multimodal references.
面向 AI Agent 的精选 Skills 集合。每一个 skill 都在日常工作中实际使用、迭代、踩过坑，覆盖内容创作、设计视觉、工具集成、合规文书等场景。
Command-line tool for distributed LLM inference benchmarks on SLURM clusters using TensorRT LLM, SGLang and vLLM.
Ready-to-run training recipes for reinforcement learning (GRPO, DAPO, GSPO, CISPO), preference optimization (DPO, ORPO), and supervised fine-tuning (SFT) on Fireworks.
A git custom command that enhances Git's native worktree functionality with interactive features, automation, and repository migration capabilities.
先归根，再分化；先明道，再造物。 从混沌需求出发，生成可运行、可验证、可进化的 Agent Skill。
"Writing doesn't just communicate ideas; it generates them."