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 server that lets AI agents drive Inkscape — interactively alongside the GUI or headlessly from the CLI
Provide the latest cryptocurrency news to AI agents, powered by CryptoPanic.
An extension of MCP for SillyTavern. A possible solution of https://github.com/SillyTavern/SillyTavern/issues/3335
Query OpenAI models directly from Claude using MCP protocol.
(formerly gsd-plugin) is a Claude Code plugin that plans, executes, and verifies your work. It asks you only about the real design and architecture decisions that need your judgment, then carries out...
An MCP server for interacting with Linear's API. This server provides a set of tools for managing Linear issues, projects, and teams through Cline.
一套建構在 之上的美股投資研究與組合管理工作區。把日報、組合檢視、個股深度分析、選擇權策略、交易日誌等流程，全部封裝成可重複執行的 slash command，並用一套**（可驗證 thesis → 證偽條件 → 機率分布 + EV）約束每一個投資結論，避免淪為 narrative。
The agent never holds a kubeconfig. Every write is policy-checked, human-approved, and traced.
mcp-repl is an MCP server that gives an agent a persistent Python or R session, kept alive across tool calls.
SolidWorks API MCP server — search API docs, examples, and enums directly from any MCP-compatible AI tool.
"It's like Gmail for your coding agents!"
OpenMessage is a local-first messaging workspace for Google Messages, WhatsApp, and Signal. Use it from the native macOS app, the localhost web UI, or any MCP-compatible client.
Agent Skills
:triangular_ruler: Ts.ED is a Node.js and TypeScript framework on top of Express to write your application with TypeScript (or ES6).
开发真正的应用很难。GSD、BMAD、Spec-Kit 等方法试图通过接管流程来帮忙。但在这么做的同时，它们剥夺了你的控制权，并且让流程中的 bug 极难排查。
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.
Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods
A Claude Code skill that consolidates scattered project markdown files into a single canonical CLAUDE.md, with a pinned PROGRESS block at the top.
Browser Harness | Self-healing harness that enables LLMs to complete any task.
Multi-agent AI development templates for opencode
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.
🚀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。
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
Shared guardrails, skills, and bootstrap scripts for AI coding agents
Skill for Claude, Cursor & Copilot that automates the Karpathy LLM Wiki workflow: ingest web, GitHub, and YouTube URLs into a well-structured, citable, cross-referenced knowledge base with automatic...