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
Drop a .pcap file, ask questions in plain English — get answers backed by real tshark data.
Give Claude on the (claude.ai) and read/edit access to files and a whitelisted shell on your local machine, over HTTPS via Tailscale Funnel, gated by OAuth 2.1. No desktop app, no device install.
Intercept AI requests, track usage, inject MCP tools centrally
The . The historical and kept only for legacy/self-hosted workflows. New users should start with the extension-first path below.
Agent Skills
一句话：输入一个基金代码，Agent 把基金经理 8 年的每一笔买卖翻出来，拿 12 个月后的真实走势逐笔验对错，最后吐出一份 700KB 的单文件交互报告——K 线战役回放、买卖点验尸、独立性审判、造神检测，全都有。
Skills, rules, and validation hooks that teach AI coding agents to generate correct UdonSharp code
The map is not the territory. Your prompt is a map; the codebase and the real world are the territory.
agnix Lint agent configurations before they break your workflow
(As usual, XKCD has a comic for this. Appropriately enough, the comic is out of date.)
Local-first harness for agent-built codebases. Humans steer, agents execute, maestro is the substrate.
AI agents like Claude Code ship features fast. AIDD Framework keeps them working, secure, and maintainable.
AI skills for PixiJS v8, the fast 2D rendering library for WebGL, WebGPU, and Canvas. They teach agents correct PixiJS usage: Application setup, scene graph, sprites, graphics, text, filters, custom...
Reusable skills and steering that teach AI coding agents how to apply the AWS Well-Architected Framework. One set of playbooks, .
Elves is an open-source Agent Skill for handing planned development or research work to a separate worker without locking the run to one model provider.
is a config-driven dev tool for Elixir projects that manages your AGENTS.md file and agent skills from dependencies. It:
Guides and production-ready commands for Claude Code: skills, subagents, hooks, memory, custom commands, and conversation-history tooling.