Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
Model Context Protocol for Wikidata
Samples for MCP servers on Windows
A remote MCP server for personal nutrition tracking — log meals with calories, macros, fiber, total sugar and caffeine, log water and body weight, review nutrition history, and import an existing...
One-command installer for integrating Google NotebookLM with OpenClaw via MCP.
A and to interact with Model Context Protocol (MCP) servers.
This repository contains a collection of Model Context Protocol (MCP) servers for Check Point security platforms, implemented in TypeScript.
A server that ingests and serves Swagger/OpenAPI specifications through the Model Context Protocol (MCP).
Transform any API into an MCP server in seconds, not hours
This project demonstrates how to build a simple MCP (Model Context Protocol) client and server using OpenAI's openai Python SDK and the mcp package.
Azure API Management acts as the AI Gateway for MCP servers.
Open Source Observability Platform for MCP Servers & Apps
Community version of MaxMCP-Dev-main
Agent Skills
把一句「把这个流程做成 Skill」，变成一个真正能被发现、能稳定触发、能通过验证、还能一键开源的 Skill。
用于 Agent Skills 的 Agnes AI 生成技能，封装 Agnes 官方文本、图片、视频 API。它采用标准 SKILL.md 结构，可安装到 Codex、Claude Code、OpenClaw、Cursor、Windsurf 等支持 Agent Skills 的客户端。
Skills for AI coding assistants (Claude Code, Cursor, etc.) that provide Databricks-specific guidance.
World-class Android pentesting skill for AI agents. It combines static analysis, dynamic instrumentation, RASP detection, authorized bypass validation, source-to-sink tracing, MASVS scoring, and...
Deep Learning Energy Measurement and Optimization
SwiftData Agent Skill for AI Coding Assistants
面向 Codex 的达芬奇自动剪辑 Agent：从任意视频、音频和图片素材出发，完成素材分析、文案创作、TTS、剪辑蓝图、DaVinci Resolve 时间线构建、成片审计与补拍建议。 A DaVinci Resolve auto-editing agent for Codex that turns arbitrary video, audio, and image media into an...
NVIDIA DeepStream SDK is a streaming analytics toolkit for AI-based video and image understanding, providing a GStreamer-based framework to build multi-stream, multi-model inference pipelines on...
Clouds Coder Cloud CLI Coder Runtime CLI execution plane × Web user plane for reliable, observable Vibe Coding.
xianxia-cinematic-video-director 是一个面向 Codex / Agent Skills 体系的东方仙侠电影视频导演 Skill。它将场景构想、图片提示词、关键帧或参考视频，扩展为具有故事推进、空间连续性、明确运镜和稳定首尾状态的多镜头视频方案。
grill-for-unknowns combines docs/source-grounded plan interrogation with the “finding your unknowns” strategy: known knowns, known unknowns, unknown knowns, and unknown unknowns.
- ❌ ：GPTZero、Originality.ai 等工具检测出 AI 生成痕迹 - ❌ ：知网、维普等平台查重率过高 - ❌ ：语言风格不符合学术规范，逻辑不够严谨 - ❌ ：手动修改效率低，难以追踪优化进度