Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers

Connect AI assistants to your terminal with full control — 36 MCP tools including SFTP support

Essential random number generation utilities from the Python standard library, including pseudorandom and cryptographically secure operations for integers, floats, weighted selections, list...

:这是一个刚刚开发的项目,功能仍在完善中,欢迎各位提出建议和改进! : This is a newly developed project with features still being refined. Suggestions and improvements are welcome!

CLI and MCP server for discovering and calling Google APIs from agents and scripts.

MCP server for Taiwan's largest job platform — search jobs, browse companies, and apply, all from Claude.

Open Swiss legal corpus + MCP server: 1M+ court decisions (1875–today), 21k laws, 10M-edge citation graph, 42 MCP tools. CC0 data, MIT code. Live at mcp.opencaselaw.ch

The watchman for your local AI agents' MCP layer.

博查是一个给AI用的搜索引擎,让你的AI应用从近百亿网页和生态内容源中获取高质量的世界知识,涵盖天气、新闻、百科、医疗、火车票、图片等多种领域。

CLI toolkit for Dynamics 365 Finance & Operations X++ development. Indexes AOT metadata, scaffolds objects, and wires up AI agents via a stable JSON envelope and MCP.

One-Click MCP Configuration Sync Tool. 中文

MCP server for Cosense (formerly Scrapbox).

База знаний по zapret2 (DPI bypass) и blockcheckw (сканер стратегий). Работает как MCP-сервер для LLM-агентов и как обычная документация.
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."