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
🔥🔒 Awesome MCP (Model Context Protocol) Security 🖥️
A simple CLI to run LLM prompt and implement MCP client.
MCP server for interacting with Neon Management API and databases
x64DbgMCPServer made from c# with Claude, Windsurf and Cursor support
基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server
This MCP server provides browser automation capabilities through Puppeteer, allowing interaction with both new browser instances and existing Chrome windows.
An SDK building Laravel MCP servers
A Model Context Protocol (MCP) server that enables AI agents and LLMs to query and analyze Prometheus metrics through standardized interfaces.
AI-powered travel hacking with points, miles, and award flights. Drop-in skills and MCP servers for OpenCode, Claude Code, and Codex.
Lean Theorem Prover MCP
MCP Server for YouTube API, enabling video management, Shorts creation, and advanced analytics
📖 Docs · ⭐ Star us · memtrace.io · npm · Discord
Agent Skills
是一个 AI Agent 技能库，收录了一系列可被 Agent 直接调用的结构化技能。每个技能都是独立的、可组合的工作流单元，覆盖信息获取、内容处理、图像工具等场景。
Binance Skills Hub is an open skills marketplace that gives AI agents native access to crypto: both centralized and decentralized.
基于 jackwener/opencli 的 Claude Code Skills 集合
A free, MIT-licensed starter kit that turns Claude Code into your personal . Audience: anyone building automations — solopreneurs, small business operators, managers, creators, AI consultants.
This repository contains skills to use with Claude Code.
面向 Web 逆向分析与接口签名还原场景的 Skill，围绕 camoufox-reverse MCP 构建单一工作流：先用 Camoufox 反检测浏览器完成网络捕获、源码定位、Hook 调试与反检测验证，再按需落地到 Node.js 或 Python 算法还原与自动化调用。
A lean .claude/ setup for daily development. Seven specialist agents, twelve workflow skills, six modular rules, and eight safety/productivity hooks.
A skill collection for creators who want to streamline writing, X Articles draft publishing, WeChat digital-asset capture, and local workflows with Claude Code and Codex.
This repository contains sample prompts and agent instructions for Microsoft Copilot, GitHub Copilot, and Microsoft 365 Copilot.
本项目把传统术数相关的 AI skill 拆成可审计、可复用、可逐步扩展的工程模块。目标不是把模型包装成“更会玄学”，而是尽量减少它在排盘、流派口径、步骤顺序和解释链路上的幻觉。
Linear Chain-of-Thought anchors on whatever it says first. Tree-of-Thought widens the search but still walks a single shared context, so the anchoring persists across branches.
This skill removes 20+ patterns of AI slop from your writing and it can also help you detect slop as well.