Claude Desktop 安装指南
支持本地 MCP 配置的桌面客户端。
MCP Servers

- ✅ vs their 5-6 basic ones - ✅ (they don't have this) - ✅ (they don't have this) - ✅ (no proxy limitations) - ✅ (vs $497/month) - ✅ (add your own features)

An MCP server that lets LLM agents play full games of Civilization VI.

A Kubernetes MCP (Model Control Protocol) server that enables interaction with Kubernetes clusters through MCP tools.

一个 MCP Server 连接所有数据库,数据库 MCP Server 的瑞士军刀。

LinkedIn prospect intelligence inside Claude — MCP server + 8 skills that research people, companies and comment threads, draft outreach, and learn what gets replies.

is a remote MCP service provided by Aqara Agent. It lets MCP-enabled AI applications securely connect to Aqara smart home capabilities.

One MCP to orchestrate them all - 98% token savings, unlimited tool access.

MCP Server for Chronulus Chat with Chronulus AI Forecasting & Prediction Agents in Claude

Local-first PC activity recorder for Windows. Captures screenshots, accessibility text, UI events, clipboard activity, and optional audio transcription into a local SQLite database — then exposes...

mcptube-vision transforms YouTube videos into a persistent, structured knowledge base using both transcripts and visual frame analysis.

XCode CLI MCP: Convenience wrapper for Xcode CLI tools & iOS Simulator. Progressive disclosure of tool responses to reduce context usage. Use --mini param for build-only with tiny context footprint.

- Learn more about the Deep Research Agent at docs.octagonagents.com
Agent Skills

Independently written prompt templates for building AI coding agents, inspired by patterns observed in Claude Code codebase.

Personal Website & Blog Theme for Hugo

An LLM-first SEO analysis skill for agent IDEs and AI coding assistants, with 16 specialized sub-skills, 10 specialist agents, and 89 scripts used as evidence collectors and workflow automation.

A CLI tool for managing and running LLM-powered agents.

将本仓库中的 skills/audit-skills/ 整个目录放置到 claude 或 codex 可识别的 .skills/ 目录下;能力范围覆盖 Java、.NET 与 PHP 审计:

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

Internal Safety Collapse in Frontier Large Language Models

Library of Growth & GTM skills + data APIs for Claude Code, Codex, Cursor to run ads, social, content, lead gen, seo and data scraping

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。

Professional white-box code security audit skill with 55+ vulnerability types, dual-track audit model, and multi-agent deep analysis.

AutoHarness Self-Learning Skills for Claude Code

OpenOPC: Build Your Personal AI-Native Company — Self-Built, Self-Run, Self-Grown