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
An MCP (Model Context Protocol) server for Tailscale, enabling detailed queries and operations for devices, DNS, users, invites, keys, webhooks, services, logging, policy validation, and tailnet...
ElysiaJS plugin for Model Context Protocol with HTTP transport
arifOS evaluates identity, evidence, authority, risk, and reversibility before an AI agent may execute a consequential action.
Get your projects MCP (Model Context Protocol) badges
is a powerful Terminal User Interface (TUI) for debugging, testing, and interacting with Model Context Protocol (MCP) servers.
An MCP Evaluation Library
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens.
MCP server for LibreNMS management
An MCP server that hosts finite state machines as dynamic resources that multiple clients can subscribe to and be updated when their state changes.
Model Context Protocol server enabling AI assistants and chatbots to access transit information through standardized interfaces.
A Model Context Protocol (MCP) server for linkedin to apply Jobs and search through feed seamlessly.
The Trend Vision One Model Context Protocol (MCP) Server enables natural language interaction between your favourite AI tooling and the Trend Vision One web APIs.
Agent Skills
This is a professional Skill toolkit for writing Chinese Party and government official documents (公文).
humble A humble, and fast, security-oriented HTTP headers analyzer
A Claude Code skill that enables AI-assisted generation of macOS/iOS Shortcuts. Create valid .shortcut plist files that can be signed and imported into Apple's Shortcuts app.
— 使用、修改或部署本專案，必須標明原作者 、附上本 repo 連結，並以相同授權公開原始碼。網路服務部署亦同。 本專案於 2026/04/13 從 MIT 切換至 AGPL-3.0。此日期之前取得的版本仍適用 MIT 授權。
Catch AI mistakes before they cost weeks of compute. Reproduce papers from arxiv. Debug runs evidence-first. Compare experiments at the right epoch. Launch with discipline.
你只说一句“我要什么视频”，它把素材、分镜、字幕、转场、动效、渲染和质检组织成一个可复现的视频工程。 Say what video you want; qiaomu-cut turns it into a source-aware, renderer-ready, verifiable video project.
A skill for AI coding agents that enables full control of Obsidian vaults from the terminal using the official (v1.12+).
微信公众号文章自动创作与发布工具:从选题搜索、撰写、AI 配图、排版到发布草稿箱,一条命令搞定。可作为 Claude Code / Codex / Cursor 的 Skill,也可独立命令行调用。
使用 LangChain 1.0 构建的 Skills Agent，演示 Skills 三层加载机制的底层原理。默认使用 Anthropic，也支持 OpenAI / OpenAI-compatible 接口。
面向电商商品图生产场景的图片套图 Skill。仓库提供一套从商品图分析、卖点提炼、Prompt 组织到成图输出的脚本与配置，适合用在淘宝、京东、拼多多、抖音等国内平台，以及独立站、Amazon 等跨境场景。
— kinetic typography, data-driven charts, explainers, TikTok / Reels, 3D & WebGL, math animation, generative illustration, and web motion. Fifteen installable packs.
Turn simple scene ideas into restrained, physically believable cinematic AIGC prompts.