Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers
MCP server for fetch web page content using Playwright headless browser.
一个基于 .NET 10 构建的现代化 AI Agent CLI，采用 Runtime First、Plugin First 架构，支持多模型、MCP、Skill、Tool、流式终端交互和可扩展插件系统。
Model Context Protocol, or MCP, is an open protocol that standardizes how applications provide context to LLMs.
Agentic AI Engineering is a production-grade engineering resource for building modern agentic AI systems with LangChain, LangGraph, RAG, MCP, local models, and deployable Python services.
Model Context Protocol (MCP) server that gives LLM agents and chatbots direct access to the World Bank's Data360 Platform.
A production-ready API gateway for Model Context Protocol (MCP) servers, providing enterprise-grade infrastructure with authentication, logging, rate limiting, server discovery, and multi-protocol...
Expose llms-txt to IDEs for development
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens.
A simple Slack bot that uses the Model Context Protocol (MCP) to enhance its capabilities with external tools.
A practical, community-driven checklist for . This guide covers local and remote MCP server risks, traffic analysis, tool-call behaviors, context boundaries, authorization flows, and unsafe code...
OmniMCP provides rich UI context and interaction capabilities to AI models through Model Context Protocol (MCP) and microsoft/OmniParser.
This repository contains sample MCP servers with rich interactive UI widgets that render inside Microsoft 365 Copilot.
Agent Skills
/brag is a Claude Code skill that turns the project you created into a short, shareable launch video — music, motion, and share copy included. One command, powered by Hyperframes.
支持 、 和 三大引擎 — 订阅 / API Key 任你选，每个 Bot 可独立选引擎。
A curated list of — AI-powered tools that live in your terminal, read/edit repos, and run commands — plus the that orchestrate, sandbox, or extend them.
Works with Claude Code, Cursor, and any agent that reads an AGENTS.md / standing-instructions file.
A set of Agent Skills that take a change from a vague idea to shipped, verified, documented code, for any AI coding agent. One skill per phase. Run only the ones a change needs, in any order.
🚀 最实用的 Claude Code Skills / Agents / Plugins 合集 | 精选 406+ | 按场景分类 | 复制即装 | 持续更新
Run /digital-marketing-pro:engagement against each brand. Same 12-Part Strategy Flow, same Four Core Documents, same 61-step structure — auditable across the entire portfolio in ~60 minutes per brand...
Curated resources for building and using Agent Skills.
Analyze a GitHub repository and summarize install steps, activity, risks, and alternatives.
Research Artifact Protocol for Rigorous and Trustworthy AI Scientists
这是悟鸣公开维护的一组 Agent Skills，偏实战、偏工作流，主要服务于 AI 工具使用、文档解读、项目配置、运维排障与技能分发。
Agentic prompt workflows as skills. Works with any agentskills.io compatible AI tool.