Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers

AI-powered travel hacking with points, miles, and award flights. Drop-in skills and MCP servers for OpenCode, Claude Code, and Codex.

Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 commands, 246 MCP tools, change-safety gates, audit evidence, zero API keys.

Spec-Driven Development MCP Server, not just Vibe Coding

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure.

HOL Guard brings antivirus-style runtime protection to AI agents. It evaluates supported agent actions and local artifacts for secret exposure, prompt injection, unsafe commands, malicious packages,...

A Model Context Protocol (MCP) server that provides tools for interacting with Trello boards.

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

Real-time data — and real trades — for Claude and any AI agent.

High-performance Model Context Protocol (MCP) server for Obsidian that provides AI tools with direct vault access through semantic operations and HTTP transport.

微信读书MCP

A Model Context Protocol (MCP) server that enables semantic search and RAG (Retrieval Augmented Generation) over your Apple Notes.

Let AI agents debug your code inside VS Code - set breakpoints, step through execution, inspect variables, and evaluate expressions. Works with , , , , , , , and any MCP-compatible assistant.
Agent Skills

这是一套可直接放进 Codex/Agent 运行环境的本地 skills,用来调用 Agnes AI 的免费文本、图片和视频模型 API。仓库只包含可复用的 skill 文件、参考文档和 Python 辅助脚本,不包含任何 API Key、生成结果或本地运行产物。

Claude Code, Cursor, Windsurf 등 Agent Skills 형식을 지원하는 AI 에이전트에서 사용할 수 있는 한국어 특화 스킬을 제공합니다.

Turn AI agents into Kaggle teammates 让 AI 智能体成为你的 Kaggle 队友 Reusable workflow for validation, modeling, Kaggle execution, debugging, ensembling, and scored submission.

Fact-checking and disinformation detection skill for Claude and Codex

Hermes SkillEval 解决一个具体问题:当 Claude Code、Codex、Cursor 一类 Agent 拥有越来越多相似的 SKILL.md 技能时,如何选中正确技能,同时识别“语义相关但 职责错误”的近邻技能,并在回归进入默认路由器前阻止发布。

Community-maintained skills for offensive and defensive security capabilities. Built for security researchers, engineers, and bug hunters.

Go-to-market skills that turn Claude into a GTM specialist. 54 skills across SEO & AI search, content, outbound, sales, growth, analytics, strategy, ads, social, and CRM.

Product Management skills framework built on battle-tested methods for Claude Code, Cowork, Codex, and AI agents.

GPU 开发 Agent Skill 集合,适用于 Cursor / Claude Code / Codex / Gemini CLI。

The canonical home for CodeRabbit's agent-native skills and plugin packaging. Use it to install AI-powered code review into 35+ coding agents, Gemini CLI, Antigravity CLI, Claude Code, Cursor, and...

Agent Skills for the Venice API. Skills are self-contained folders of instructions (one SKILL.md each) that an LLM agent loads on demand to work correctly against a specific surface area of the API.

Open-source agent skills for debugging and optimizing Apache Spark workloads