Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Give Claude on the (claude.ai) and read/edit access to files and a whitelisted shell on your local machine, over HTTPS via Tailscale Funnel, gated by OAuth 2.1. No desktop app, no device install.
Sovereign, encrypted, portable memory for AI agents.
Your digital developer twin — because "explain our setup again" gets old fast.
A library built on top of the MCP TypeScript SDK that makes it easier to implement MCP with auth into your MCP client and/or server.
OpenPets is a native macOS desktop pet for visible agent progress, review prompts, completion states, and lightweight animations across local coding tools.
An MCP server that connects to a Swagger specification and helps an AI to build all the required models to generate a MCP server for that service.
A Stdio MCP server which proxies an SSE MCP server.
Transparent MCP proxy that reduces the token cost of large upstream tool responses for nearly every other MCP server imaginable.
MCP server to enable an LLM to do basic static triage of a PE.
MCP server to extract contents from a PDF file
Shared MCP server for the Upvote.club Public API.
The Open Source Analytics and Visibility Layer for ChatGPT Apps and MCP Apps.
Agent Skills
本 Skill 将数学建模任务拆分为 三个阶段。既可以按顺序完成整道题，也可以只执行其中一个阶段。
Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.
面向设计奖全流程的证据驱动 Agent Skills：从获奖案例检索、设计评价和奖项匹配，到申报文字准备与提交终检。
A curated library of 38 hand-crafted, lawyer-verified legal reasoning skills for PRC statutory law.
This repository is where common agent skills that should be shared across repositories go.
AutoSkill is a practical implementation of . It learns from real interaction experience (dialogue + agents), automatically creates reusable Skills, and continuously evolves existing Skills through...
Professional software engineering skills for AI coding agents. Transforms code into senior-engineer quality software through SOLID principles, TDD, clean code practices, and professional software...
The most autonomous agent framework. Give it a direction and it gets the work done: ships features to your repos, finds and privately discloses real vulnerabilities, deploys live apps, runs deep...
Know what a skill can do before you trust it.
Modular instruction packages that give AI coding assistants on-demand capabilities for specific tasks, working across Cursor, Claude Code, GitHub Copilot, and more.
An AI coding agent skill for deep architectural analysis of open-source projects. Generates professional-grade architecture reports with design insights, trade-off analysis, and Mermaid diagrams.
SkVM is a compilation and runtime system that makes LLM agent skills portable across heterogeneous models and harnesses. It has four major parts: