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
Access thousands of AI prompts directly in your AI coding assistant
This is an MCP server that integrates PRD and TRD building tool Nautex AI with the Coding Agents.
A middleware server that enables multiple isolated instances of the same MCP servers to coexist independently with unique namespaces and configurations.
MCP server + prompt that turns any AI coding agent (Cursor, Claude Code, Cline, Kiro, Windsurf…) into your Digital Twin — generate a project-specific AGENTS.
- The docker image is 2GB without pre-downloaded models. Its 3.76GB with pre-downloaded models!! Too big, someone please help me to reduce the size.
MCP server giving LLMs the ability to design, simulate, and analyze SPICE circuits via LTSpice and NGspice
MCP server for the Hotwire Club knowledge base - provides tools for searching, browsing, and discovering documentation from the Hotwire Club knowledge base.
Frame0 is a Balsamiq-alternative wireframe tool for modern apps. allows you for creating and modifying wireframes in Frame0 by prompting.
iPhone MCP server that lets AI use iPhones
Playwright for the shell - MCP server for terminal recording and automation
MCP server for Apple iWork automation — 113 tools for Numbers, Pages, and Keynote. Template discovery, Creator Studio AI tools, compound batch operations. One line to install.
91% of Deep Research quality · 5% of the cost · Works in every MCP client
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."