Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
A robust MCP (Model Context Protocol) server providing comprehensive integration with Things3, allowing you to create, manage, and search tasks and projects through the MCP protocol.
Gives Claude the ability to remember your conversations and learn from them over time.
An MCP (Model Context Protocol) server that provides PDF manipulation tools. This server allows LLMs to perform operations like merging PDFs and extracting pages through the Model Context Protocol.
This project implements a Model Context Protocol (MCP) server for interacting with the Semantic Scholar API.
An MCP (Model Context Protocol) server that brings Superdesign - an open source AI design agent by @jasonzhou1993 and @jackjack_eth - to Claude Code as native tools.
A Model Context Protocol (MCP) server that provides for game hacking through Frida. Enables AI assistants and automation tools to perform memory scanning, value modification, pattern matching,...
A Model Context Protocol (MCP) server that connects AI assistants to SemaphoreUI - enabling natural language control of Ansible automation.
Model Context Protocol (MCP) server that lets MCP clients control and inspect DaVinci Resolve (including Fusion) through tools and resources.
An MCP (Model Context Protocol) server for structured, iterative reasoning. CRASH helps AI assistants break down complex problems into trackable steps with confidence tracking, revision support, and...
HexDocs MCP is a project that provides semantic search capabilities for Hex package documentation, designed specifically for AI applications. It consists of two main components:
An open-source MCP server that turns LLMs into condition monitoring assistants for reliability engineers. Its core design rule: .
A Model Context Protocol (MCP) server that provides AI assistants with structured access to your Logseq knowledge graph.
Agent Skills
An Agent Skill that reviews scientific and engineering manuscripts for writing quality, applying the methodology from Dr. Kristin Sainani's Writing in the Sciences course at Stanford (2012).
Generate and evaluate agent skills based on traces with agents. Create skills with teacher models (expensive/slow) that student models (cheap/fast) can use to perform harder tasks reliably.
The central challenge in AI development isn't a lack of ideas, but the inconsistent process of turning them into robust, reliable skills.
This repository is built for AI infrastructure engineers who want agents to do real work, not recite generic prompts.
Open-source, local-first video editor where creators and AI agents edit the same real timeline.
Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.
Making ANY Software Skill-Native The meta-skill that generates production-ready Skills for AI agent platforms.
给 Agent 一条 URL，直接拿到正文、图片和元数据；不启动浏览器，不把整页 DOM 塞进上下文。 English · 简体中文
Expert guidance for any AI coding tool that supports the Agent Skills open format - modern Swift Testing APIs, XCTest migration, parameterized tests, traits/tags, async testing, and parallel...
— добавляются новые возможности, отлавливаются и исправляются баги, производится оптимизация. Следите за обновлениями.
A production-ready OpenClaw plugin that implements the A2A (Agent-to-Agent) v0.3.0 protocol, enabling OpenClaw agents to discover and communicate with each other across servers — with zero-config...
Xiaohei 2.0 Codex Skill for Chinese real-object article illustrations and long-scroll story images