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
Burp MCP proxy with compression pipeline — reduces 182KB responses to ~4KB
AI agents control Figma through code execution.
arcticdb-mcp An MCP server for structured read/write access to ArcticDB. Overview • Demo • Quick Start • Configuration • Tools • Development
Infinite text-free AI image generator + SQLite-indexed multilingual vault & gallery — with a local MCP your AI can drive.
Local-first multi-runtime AI cockpit (CLI + desktop + MCP). War-rooms, review receipts, open multi-model coding benchmarks. MIT.
Security review mascot logo for the DocSentinel console and documentation.
MCP Slim Guard gives a host one deliberate way to reach authorized upstream tools. It keeps input schemas intact, validates calls before the upstream is invoked, and can recover an oversized result...
CLI and MCP server for discovering and calling Google APIs from agents and scripts.
CLI toolkit for Dynamics 365 Finance & Operations X++ development. Indexes AOT metadata, scaffolds objects, and wires up AI agents via a stable JSON envelope and MCP.
Local MCP server for COMSOL modeling workflows, validation, and RAG-assisted multiphysics automation.
An MCP server for AI agents to automate token swaps on Uniswap DEX across multiple blockchains.
Scout’s local MCP puts metrics, traces and errors right in your AI agent. For teams that do it all.
Agent Skills
see README.en.md for the full English version.
Your AI watches your workflows and turns them into reusable Hermes skills — automatically.
Fusion-Fable is a Claude Code skill that runs a hard question through a pipeline. The same prompt is dispatched to several models in parallel — each answering independently with web search and bash,...
Empirically detect the repetitive defaults a model falls back on, then turn those findings into a reusable instruction file that makes future outputs less generic.
这份 Skill 的目标很明确：中文技术写作应更克制、更准确、更易读。不追求宣传感，也不试图把所有内容都写成统一模板，而是聚焦几类高频问题：
Desktop AI assistant powered by Claude API
A collection of Claude Code skills for academic research review. This tool was developed by Claes Bäckman.
Turn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file.
Official skills for the GLM family of models, designed for agent architectures including Claude Code, OpenCode, OpenClaw, AutoClaw, and other AI coding agents.
⛏️ Turning data into a visual language for better thinking with Skills.
WeChat chat history analyzer — runs in Claude Code, generates dual-user visualization + AI personality comparison report. No API key needed.
Tools for empirical economics research with Claude Code — audit protocols, presentation systems, PDF workflows, and a research GTD harness.