Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers

A Model Context Protocol (MCP) server that provides seamless integration with the Postman API. This package enables AI assistants and applications to interact with Postman workspaces, collections,...

MCP server for interacting with CodeRabbit AI reviews on GitHub pull requests

Minimal Metals stand alone client that allows running the metals mcp server

Self-hosted, OpenAI-compatible RAG API + MCP server that plugs local knowledge into existing LLM clients.

Garry's Mod external console software with MCP and Websocket support.

Tiger GitHub MCP server

Official Anam AI MCP server for managing AI avatars

Official Porkbun MCP server — exposes the Porkbun v3 API as 30 native tools for Claude Desktop, Cursor, and other AI agents. Idempotency-safe writes, full domain lifecycle.

A unified plugin for developers integrating MCP servers into modern JavaScript build tools, including Webpack, Rollup, Vite, and more.

Keryx: The Fullstack TypeScript Framework for MCP and APIs

זה ממש אבל ממש לא אמסיפי לחילנט

An MCP-capable intelligent RSS feed ingestion and summarization to markdown tool.
Agent Skills

A personal collection of agent skills

基于任务类型动态调度到合适的智能体角色(架构师、产品经理、测试专家、独立开发者)。支持多智能体协作、共识机制和完整项目生命周期管理。

Easy, fast, and memory-efficient structure prediction inference

🌊 CLI tool for RTL waveform (VCD/FST/FSDB) inspection

Codex and Claude Code BaZi skill for 八字排盘, Zi Wei, true solar time, compatibility and auspicious timing

ChatGPT Team Bug号自动注册;包含自动注册SKILL和自动注册脚本。慢一点儿,但是交给Agent,他自己能完成全部流程。推荐使用Codex

一套可直接使用的 Agent skill 工具包——从 165 个顶级 AI 产品系统提示词中,蒸馏出 15 个可复用的系统提示词设计模式。

Work seamlessly with Glean from your command line.

24 Agent Skills for Claude, one folder per skill, each a SKILL.md plus, for the quantitative ones, a bundled Python calculator.

我在小红书账号 分享自己实际使用的 AI Skill、投研工作流、技术研究方法和内容生产实践。小红书笔记负责解释“为什么值得这样做”,这个仓库负责提供“怎么让 Agent 真的去做”。

ChatGPT/OpenCode/Claude skill: Xiaohongshu AI-tools writing workflow

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.