Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
MCP-PDB provides tools for using Python's debugger (pdb) with Claude and other LLMs through the Model Context Protocol (MCP).
MCP server built on Phoenix Framework (Elixir). Exposes Server-Sent Events and JSON-RPC endpoints for MCP clients, with support for managing multiple child MCP servers through JSON configuration.
一个专业的、AI驱动的图表与原型绘制MCP服务器。它深度集成了智谱AI、OpenAI、Gemini等多种大语言模型，能够根据自然语言描述，智能生成**的 draw.io 格式图表和 HTML 交互式产品原型。
An MCP (Model Context Protocol) server that enables AI assistants to analyze and summarize YouTube videos by extracting captions, descriptions, and metadata.
AI-powered browser testing via the Model Context Protocol. Point it at any URL (or localhost) and describe what to test — an AI agent browses your app and returns pass/fail with screenshots.
A Model Context Protocol (MCP) server for Gradle. It gives AI agents the tools they need to explore project structures, run tasks, audit dependencies, and interact with the JVM runtime.
Think MCP is an implementation of an MCP (Model Context Protocol) server that provides a "think" tool for structured reasoning in agentic AI workflows.
BloodHound MCP (Model Context Protocol) is an innovative extension of the BloodHound tool, designed to enable Large Language Models (LLMs) to interact with and analyze Active Directory (AD) and Azure...
Convert any MCP server into a Claude Skill with 90% context savings.
This is a Model Context Protocol (MCP) server that provides tools for interacting with Proxmox VE infrastructure.
connects AI agents to ITASCA's numerical modeling software — PFC, FLAC, 3DEC, MPoint, and MassFlow — through the Model Context Protocol.
A headless Ghidra server that speaks MCP (Model Context Protocol), giving AI agents full access to deep reverse-engineering workflows: program lifecycle, disassembly, decompilation, patching, types,...
Agent Skills
Claude skills for Swedish accounting compliance. These skills give Claude deep knowledge of Swedish bookkeeping law, tax rules, and reporting requirements, useful for any developer building...
Six packaged Claude skills for core product marketing work: context setup, messaging, competitive intelligence, customer research, go-to-market planning, and pricing.
Turn Claude into a disciplined research analyst — verify facts against primary sources, brief any topic, draft flagship reports. Standalone or chained; runs across LLM terminals.
两者都输出 HTML slides。但出发点不同：这个 skill 的每一个决策——叙事结构选什么、每张 slide 用什么布局、用什么动画——都来自一个问题：
中文社群最完整的 Claude Code 進階指南 — 涵蓋 CLAUDE.md 架構設計、Skills 撰寫、Subagent 編排，附可直接使用的實戰範例。
- — ~/.ielts/ 跨会话记忆，所有训练数据自动存档 - — 每篇作文/阅读/听力自动归档，带评分 - — 自动统计四科趋势 - — 本地 React 网页：趋势图 / 雷达图 / 错题热力图 - — 自动聚合高频错误标签 - — 跨篇累计，可搜索 - — 数据驱动诊断 + 个人化训练计划 - — 题型追踪 + 精听任务 - — 间隔重复 + 同义替换专项 - — 一键 backup /...
A Git-based package manager designed for AI-assisted development, similar to npm but supporting skills, agents, commands, hooks, and any AI resource types.
CLI tools skills for AI coding assistants (Claude Code, Codex, Antigravity CLI).
Sage is an AI agent that handles your X/Twitter content strategy end-to-end. Voice calibration. Trend scouting. Tweet drafting. Thread writing. Performance tracking. Feedback loop.
A Claude Code skill for naming products, SaaS tools, brands, and projects.
Claude Code skill: auto-scan SKILL.md / prompt / codebase for duplicates, naming drift, modularizable blocks, oversized files. Companion to claude-skill-social-post.
6.0 · Public Edition May 2026 — v6.0 adds (quarterly forecasting + inline assumption mirrors + 3 new QC checks) on top of v5.0's three-layer defense system Claude Code / Cowork (Anthropic)