Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers

Manage test cases, execute manual or automated tests, debug issues, and even fix code—directly within tools like Cursor, Claude, or any MCP-enabled client, using plain English.

One config to rule them all. Practical standard layer for multi-LLM development.

MCP server giving LLMs the ability to design, simulate, and analyze SPICE circuits via LTSpice and NGspice

MCP server for Apple iWork automation — 113 tools for Numbers, Pages, and Keynote. Template discovery, Creator Studio AI tools, compound batch operations. One line to install.

Discover, install and manage MCP servers on macOS

Python MCP Server for Kestra — you can use it as a tool in Kestra's AI Agents

A production-ready iOS automation MCP server built with FastMCP 2.0, featuring clean modular architecture with complete platform segregation.

High Performance MCP server + client for Windows and macOS computer control built in Rust. Screenshot, mouse, keyboard, clipboard, and app management — all in-process via Rust NAPI.

MCP OCR module using macOS Vision framework

MCP server providing systematic thinking, mental models, and debugging approaches for enhanced LLM problem-solving

Agents Council The simplest way to bridge and collaborate across AI Agent sessions

Control DaVinci Resolve from AI assistants (Cursor, Claude) via MCP. Full read + write bridge with 44 tools and local Whisper transcription.
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