Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers
🚀 Generate executable TypeScript tools from MCP servers with 98% token savings. Progressive loading pattern for AI agents. Production-ready.
A monorepo of Unraid tooling: two MCP servers (Python and Rust) and three Unraid OS plugins, plus the Claude/Codex agent integrations that surface them.
The agent never holds a kubeconfig. Every write is policy-checked, human-approved, and traced.
Opencode-Raven keeps noisy tool work behind a focused Raven agent, so your main model gets compact answers instead of raw search results, docs pages, GitHub examples, MCP output, or large MCP schemas.
一个MCP服务
Build ToolJet apps end-to-end via governed MCP tools and an app-builder skill.
MCP server that gives AI assistants direct access to ngspice circuit simulation — design, simulate, and verify circuits through natural language
An MCP App for AI-powered video creation. It combines an MCP server with an interactive View — the model writes React/Remotion code, the server compiles it in real-time, and a live video player...
GUI + MCP control plane for your local dev servers. Humans click, agents automate the same daemon.
An MCP server that exposes the Revit API docs and sample code to LLMs.
A Roslyn-based MCP server that gives AI agents deep semantic understanding of .NET codebases — type hierarchies, call graphs, DI registrations, diagnostics, refactoring, and more.
Code Mode MCP — aggregate all your MCP servers behind search() + execute()
Agent Skills
Pi package with agent-first skills and prompt templates for structured codebase understanding, safe greenfield starts, safe changes, architecture-aware review, structured-doc validation, and...
🚀面向求职与开发场景的实用 AI Skills 集合，支持简历优化、岗位投递、面试准备与开发提效。
"Where'd you get that prompt?! It's lovely!" "Oh, this old thing? I got it at JeffreysPrompts.com."
J-Space Cognition Suite V3.7 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace research. | 哔哩哔哩：Tiger380 (UID 3494375382321675) — https://space.bilibili.
Harness-enforced AI business research skill for Claude Code and Codex Desktop
If you'd like to support these efforts consider becoming a paying Patreon member ❤️ You'll even get access to up to date lessons and other perks: patreon.com/TheHotwireClub
这是一个领域无关的 AI Context 工作区模板，用于为任意类型的多轮 AI 协作提供稳定、可追踪的上下文结构。
An autonomous agentic harness for Kubernetes. Proactive fleet audits, declarative GitOps remediation, and ChatOps in one place.
Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods
一个基于 DeepAgentsJS 的智能助手，参考了OpenClaw的设计理念。具有自主记忆和SKILLS编写/执行能力。
This repo contains Tizen documents for platform and application developers.
Curated, security-first OpenClaw skills (Markdown-based). Security audit skills - detect prompt injection, supply chain attacks, credential leaks. Works with Codex CLI, Claude Code, any LLM.