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
A Docker-based server that gives AI agents (GitHub Copilot, Claude, etc.) direct access to a full Kali Linux penetration testing toolkit.
An MCP (Model Context Protocol) server that exposes Google Jules Agent operations via FastMCP.
A Model Context Protocol (MCP) server that provides tools to interact with Storybook documentation and component information.
A Model Context Protocol (MCP) server that provides advanced HTTP request capabilities for Claude and other LLMs.
A Model Context Protocol (MCP) server that provides tools for reading and extracting text from PDF files, supporting both local files and URLs.
inspiration from https://github.com/mark3labs/mcphost
A Model Context Protocol (MCP) server implementation that integrates Nuclei, a fast and customizable vulnerability scanner, with the MCP ecosystem.
A Model Context Protocol (MCP) server for searching and retrieving Solodit vulnerability reports.
This is a Model Context Protocol (MCP) server for interacting with AIStor object stores.
— Model Context Protocol (MCP) gateway for Telegram. 8 context-efficient tools, multi-tenant, MTProto bridge.
Model Context Protocol server for clangd on large C++ codebases.
Aircrack-MCP is a Model Context Protocol (MCP) server that enables large language models to interact with Aircrack-ng tools.
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。
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。
Claude Code를 위한 커스텀 스킬 모음입니다. 개발 생산성을 높이기 위한 다양한 자동화 스킬들을 제공합니다.
A personal AI assistant that evolves with you. 8 different types of memory (episodic, semantic, procedural, emotional, prospective, behavioral, narrative, shared) make it truly yours.
A lean .claude/ setup for daily development. Seven specialist agents, twelve workflow skills, six modular rules, and eight safety/productivity hooks.
Ported from the TypeScript reference implementation and extended with a Python-native runtime
A self-evolving AI research colleague for scientists.
CAR is a meta-harness for coding agents (Codex, Hermes, OpenCode, OMP, anything ACP). It is not a coding agent itself. You bring the plan and the agents; CAR coordinates the long-running execution.
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。
the interactive repo-local install paths (./install.sh and clawhip install from a clone) can offer to star this repo after a successful install when gh is installed and authenticated.
1. 对话 skill 模式：在聊天中按 SKILL.md 约束执行单轮改写；安装本仓库作为 skill 后即可直接使用。 2. 脚本 API 模式：通过 scripts/run_aigc_round.py 执行单轮分段处理，并按需调用外部 OpenAI 兼容接口。 3. Web 模式：启动本地后端和前端页面，在浏览器中完成上传、配置、执行和导出。 4. app：安装app可直接使用
Wakaru unpacks webpack, esbuild, and other production bundles, then reverses minifier and transpiler output into readable modern JavaScript.