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
Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses,...
next-devtools-mcp is a Model Context Protocol (MCP) server that connects coding agents like Claude and Cursor to your running Next.js dev server.
MCP Server for Metasploit
Enable your AI agents to read, analyze, and modify Figma designs.
A Playwright-based Node.js tool that bypasses search engine anti-scraping mechanisms to execute Google searches and extract results.
Feishu / Lark 飞书文档与任务管理工具，支持 MCP 服务器和 CLI + Skill 两种使用方式，可无缝集成 Cursor、Claude Code、Cline 等 AI 编码工具
MCP server to access Garmin data
飞书/Lark官方 OpenAPI MCP
160+ animated, accessible, production-ready components — delivered as raw source code, owned by you forever.
MCP server for long term agent memory with Mem0. Also useful as a template to get you started building your own MCP server with Python!
A simple CLI to run LLM prompt and implement MCP client.
Official Jina AI Remote MCP Server
Agent Skills
A Claude Code skill for generating and editing images using the Gemini CLI's nanobanana extension.
Claude Design on claude.ai is excellent. But it's locked.
每支教學影片都會附一個 MD 檔（懶人包），丟給 Claude Code 桌面版就能自動完成。
语雀 AI 生态官方分发仓库 一套知识管理 Skills，任意 AI 客户端开箱即用。
An iterative deep-logic security audit agent for Claude Code. Nemesis combines two complementary audit methodologies in an alternating feedback loop to find bugs that neither can catch alone.
Skill packs - BMAD, Spec-Kit, mattpocock/skills - teach your AI coding agent how to build. None of them remember who the client is, what you promised them, or who agreed it was delivered.
31 skills for Claude Code covering the full academic research paper lifecycle — from literature search to slide generation — plus GitHub repository analysis for research topics.
一个 Claude Code skill：把一份参考 Word (.docx) 的排版样式（字体 / 字号 / 缩进 / 行距 / 对齐 / ）**复刻到新内容上。
Fable5 구조를 넣은 Sonnet이 Opus와 블라인드 테스트에서 사실상 비겼다!! 그것도 답 1건당 비용 3분의 1로!! Sonnet + Fable 5 structure virtually tied Opus in a blind test — at 1/3 the cost per response. (bench/)
A skill catalog that won't let you spend 6 months on a research gap that's already closed, isn't a real contribution, or isn't feasible.
gentle-pi installs in Pi: a senior-architect operating layer for Spec-Driven Development, focused subagents, strict TDD evidence, reviewable work units, safety guards, project/user skill discovery,...
Automatically download books from Anna's Archive and upload them to Google NotebookLM with one command.