Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Apple Store Connect MCP Server for Claude AI - iOS-compatible OAuth with comprehensive App Store Connect API integration
By transforming source code into a queryable Semantic Graph and a structured AST, this tool bridges the gap between "reading text" and "understanding structure.
This project implements a Model Context Protocol (MCP) server for GitHub API access. It provides a set of tools that allow LLM agents to interact with GitHub repositories, issues, pull requests, and...
Maintenance of a set of tools to enhance LLM through MCP protocols.
An MCP Server to enable global access to Rememberizer
A simple note-taking MCP server for recording and managing notes with AI models.
MCP Server for Perses
AI-powered FL Studio control via the Model Context Protocol. Beyond piano-roll notes — full in-DAW mixing (Mix Doctor, gain staging, EQ/comp/reverb, reference matching), routing, and composition...
Sweet Home 3D plugin that embeds an MCP server — lets Claude control Sweet Home 3D over HTTP
An MCP server for code reviews using OpenAI and Google models for Claude-code
Use MCP to control Recaf4.0 to achieve methods like decompile/rename
A lightweight Model Context Protocol (MCP) server that enables AI assistants like Cursor & Claude to read from and write to your Obsidian vault.
Agent Skills
Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.
A skill bundle in Claude Code Skills format. It covers the 100 most-used Bioconductor packages the top 100 rising-star packages (newly released since ~2021 and fast-growing) from the BioMate-KB...
Write a SKILL.md, drop in some evals, and find out — empirically — whether your skill actually makes the model better at the task.
Vibe-coded products are ugly in the same specific way: indigo gradients, glowing cards, emoji everywhere, a mascot in every corner, ALL-CAPS stat-cards.
Thirteen curated Agent Skills package the steps, templates, scripts, examples, and quality gates behind repeatable work. They follow the open SKILL.
The easiest way to evaluate your Agent Skills. Tests that AI agents correctly discover and use your skills.
Demo: Analyzing 2 years of NVDA, AMD & SPY stock data (15,000+ lines of raw JSON) using DeepSeek V3.2
A source-available Codex skill for distilling photographs into sparse editorial abstractions.
这里不是一叠孤立的提示词。每个 Skill 都用 SKILL.md 固化触发条件、工作阶段、确认门槛和交付物，让 Codex、Claude Code 等 Agent 在产品、开发、研究、写作和日常效率任务中按同一套方法工作。
A curated marketplace of Claude Code plugins for software engineering workflows.
One command. 25 agent skills. Zero to profitable business.
- 🤷 "AI到底能帮我做什么？" —— 听了100场演讲，还是一头雾水 - 💸 "我该先投哪个方向？" —— 怕投错钱，更怕错过窗口期 - 📊 "别人都在用AI了？" —— 焦虑但不知道从哪开始