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
MCP OCR module using macOS Vision framework
Quickstart · Configure your client · Comfy Cloud MCP · Tools · Contributing
Your AI conversation history, queryable from any MCP-aware LLM, stored entirely on your machine.
MCP server providing systematic thinking, mental models, and debugging approaches for enhanced LLM problem-solving
MCP server that connects Claude to Cavalry animation software. Create layers, set attributes, animate with keyframes, render frames, and more — all through natural language.
A MCP server that send desktop notifications with sound effect when agent tasks are completed.
This server uses the Tavily API to perform searches based on specified queries. - Search results are returned in text format.
Control DaVinci Resolve from AI assistants (Cursor, Claude) via MCP. Full read + write bridge with 44 tools and local Whisper transcription.
Local MCP server that gives AI coding agents persistent, searchable memory of your codebase
Community-maintained MCP server for Wireshark / tshark. Not affiliated with Wireshark or Anthropic. Give your AI assistant direct access to packet captures. Ask Claude to summarize a .
Simple MCP Server to enable a human-in-the-loop workflow in tools like Cline and Cursor. This is especially useful for developing desktop applications that require complex user interactions to test.
A local MCP server that connects Claude Desktop (or any MCP-compatible LLM) with your Evernote account, allowing contextual queries and searches over your notes using natural language.
Agent Skills
Long-horizon agent skill for Claude Code / Cursor / Codex / Grok Build — multi-task ledger loop, host-portable, clean-context supervisor, verified gates.
一个用于生成 B/C 端产品原型的 Codex Skill，重点面向 Figma 可编辑 UI 原型。
你可能需要花时间整理材料，把问题发给大模型，review大模型给的答案，再去尝试理解某些晦涩的概念，并判断大模型的回答是否足够可信。忙完以上的一切，还要忙着去除人机味
An agent skill that turns — a codebase, an architecture doc, or a plain-English description — into an : monospaced, organized into colour-coded planes, with pan/zoom, click-to-isolate focus, a...
它扣掉的只有两件事：固定 IP 形象和固定配色。使用者只需要填写自己的 IP 角色公式和品牌配色，就可以把文章、知识点、教程内容转成一套带个人风格的配图 Prompt。
zotero-literature-visualizer 是面向 Codex 的学术文献工作流 skill。它可从研究主题或已有 Zotero 文献库出发，完成文献检索、期刊质量核查、已有本地 PDF 的全文整理、Zotero 条目整理、中英文研究摘要，以及交互式文献 dashboard 的生成。
- — wrap third-party SDK clients (Stripe, Resend, AWS, etc.) with Effect using the "use" pattern: type-safe tagged errors, automatic tracing spans, config-based secrets, and clean dependency...
This repository is the canonical source for a simple cloud factory: a set of agent skills and GitHub Actions workflows for moving work from an incoming issue to a verified change.
把投资人 的"供应链卡点逆向"投资逻辑和方法论操作化的** —— 不是模仿他说话，而是用他**的方式，帮你分析一只票 / 一个板块 / 一个 thesis。
A free, open set of Agent Skills for short-form video creators, sponsored by Vyral Content.
A Google Apps Script library to seamlessly integrate the Gemini API for processing files, unstructured data, and building autonomous AI agents.
claude code / codex skill , 一个让 AI 帮你 5 分钟深度调研任意中国城市周末玩法的agent skill, 寻找精神旷野：户外消费告别长途远行、装备内卷，转向日常低成本微沉浸；菜市场、城市老街成为年轻人精神微旅行目的地，CityWalk 演化成主题探索路线，日常场景即可实现情绪解压。