Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Universal AI Tool Orchestrator - Sync skills, MCPs, and memory across Claude Code, Codex, Gemini CLI, OpenCode, OpenClaw...
188+ local tools for Claude, ChatGPT, Cursor & Grok — Mail, iMessage, Teams, Slack, WhatsApp, OneDrive, Google Drive, Zoom, Outlook, Office. Native macOS, 100% local, no API keys.
Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero cloud dependency
You built an agent. Now you need to tune the prompt. Swap the model. Restrict access for specific users. Figure out what it's actually costing you.
MCPSafari: Native Safari MCP Server for AI Agents
The enterprise-grade TypeScript framework for building production-ready MCP servers. Decorators. Dependency Injection. Widgets. One framework to ship AI-native backends.
CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable.
An MCP Server implementation that integrates the Brave Search API, providing, Web Search, Local Points of Interest Search, Video Search, Image Search, News Search and LLM Context Search capabilities
Advanced search and retrieval for web crawler data. With , your AI client filters and analyzes web content under your direction or autonomously.
Find local coding-agent sessions and copy their user and assistant messages into another agent's native format. TUI, CLI and MCP.
A modular MCP server providing AI-driven vulnerability management skills, including severity classification and automated insights.
Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6% measured savings, reproducible.
Agent Skills
本仓库是一套面向 的白盒代码安全审计 Skill 集合，覆盖「路由枚举 → 鉴权建模 → 数据流追踪 → 分类漏洞审计 → 证据一致性校验 → 报告汇总」全流程；在 Cursor 等环境中以 的方式落地。
一个安全测试专家技能（Agent Skill），将 WooYun 88,636 个真实漏洞案例、先知 5,600+ 篇研究文档、GAARM 173 条 AI 安全风险（5 域）、OWASP LLM/ASI/WSTG 三大框架与 200+ 常用测试用例，浓缩为可按需加载的实战渗透测试知识库——让 AI 助手在安全评估中即时调用系统化的攻防知识。
A collection of agent skills maintained by @mizchi, distributed via APM (Agent Package Manager).
image-to-code is a Codex skill for turning a selected UI image, screenshot, or Figma export into an adaptive code implementation, high-density transparent PNG assets, and optional editable Figma...
With GMGN Agent Skills, you can use AI agents to query real-time trending token rankings across multiple chains, token fundamentals, social media signals, live trading activity, new tokens in...
We welcome issues and pull requests for missing work on harness agents, agent skills, memory, self-improvement, agent RL, evaluation, and safety.
A pi extension that bridges Discord and Telegram channels to a sandboxed pi session. Each connected channel gets its own Gondolin micro-VM with persistent workspace, shared storage, memory, and...
Academic Figure Skill 面向学术级科学图表生成Skill，可自动完成从数据解读到顶刊格式图表生成的全流程。 问题驱动 · 8 步闭环工作流 · 29 种图型 · 四轮 QA 协议 · 矢量 PDF 交付 · 统计报告 项目介绍 · 安装与使用 · 图表类型 · 工作流 · 项目结构 · 质量评估 · 贡献指南 · English
Given an investment , this skill reverse-maps the supply chain to surface — distilled from the publicly shared methodology of X/Twitter trader .
输入中文文章内容 → 输出怪诞手绘风格配图。开源 AI Agent Skill。 Skill 代码采用 MIT License；Gimi 角色形象见 IP-NOTICE.md。
Building Claude Code Using Harness Engineering
"It is remarkable how much long-term advantage people like us have gotten by trying to be consistently not stupid, instead of trying to be very intelligent."