一种用于私有优先分发代理（技能、代理和提示）的元技能，跨越代理、设备和团队。

这是给谁的

如果你是一名工程师，使用代理处理10+代码库，并且正在构建专业的个人技能、代理和提示词——这正是为你设计的。

如果你只在一两个仓库工作，就不需要这些。如果你安装了公开互联网的技能却没有审核，这也不适合你。

图书馆解决了一个特定问题：你构建了分散在仓库、设备和团队中的强大代理。它们被重复、不同步且难以协调。这为你提供了一个单一的参考目录，可以私密分发它们。

这是什么

库是一个单一技能，唯一职责是管理其他技能。它是一个引用目录——本地文件路径和GitHub仓库网址——指向你的代理代码所在位置。除非你提出要求，否则不会复制或安装任何东西。

可以把它看作是代理能力的package.json——但你管理的是技能、代理和提示，而不是包。你指向的是自己的私有GitHub仓库和本地路径，而不是注册表。

**这是纯粹的代理应用。

The Library

A meta-skill for private-first distribution of agentics (skills, agents, and prompts) across agents, devices, and teams.

Who This Is For

If you’re an engineer working on 10+ codebases with agents and you’re building specialized private skills, agents, and prompts — this was made for you.

If you work in one or two repos, you don’t need this. If you install skills from the public internet without reviewing them, this isn’t for you either.

The Library solves a specific problem: you’ve built powerful agentics scattered across repos, devices, and teams. They’re duplicated, out of sync, and hard to coordinate. This gives you a single reference catalog to distribute them privately.

What It Is

The Library is a single skill whose only job is to manage other skills. It’s a catalog of references — local file paths and GitHub repo URLs — that point to where your agentics live. Nothing is copied or installed until you ask for it.

Think of it as a package.json for agent capabilities — but instead of packages, you’re managing skills, agents, and prompts. Instead of a registry, you’re pointing at your own private GitHub repos and local paths.

This is a pure agent application. There are no scripts, no CLIs, no dependencies, no build tools. The entire application is encoded in SKILL.md and a set of cookbook instructions that teach the agent exactly what to do. The agent IS the runtime. This matters because:

• Any agent harness that reads skill files can run it (Claude Code, Pi, etc.)
• You can modify behavior by editing markdown, not code
• The skill can be extended, forked, and adapted instantly
• An orchestrator agent can chain library commands without any tooling overhead

Why It Exists

As you build with AI agents, you accumulate skills, custom agents, and prompts — potentially hundreds of them. You need to:

• Reuse them across projects without copy-pasting
• Distribute them to your agents running on other devices (Mac mini, remote servers, cloud sandboxes)
• Share them with your team without making everything public
• Keep them private — these are specialized capabilities built for competitive edge
• Stay in sync — one source of truth, not 10 stale copies

Existing solutions don’t fit:

• Global ~/.claude/* — exposes everything to every agent. Global is the opposite of specialized.
• Claude Code plugins — requires marketplace infrastructure, manifests, and locks you into one platform.
• Single monorepo — doesn’t reflect reality. You build agentics in specific codebases for specific use cases.

How It Works

The Catalog (library.yaml)

default_dirs:
  skills:
    - default: .claude/skills/
    - global: ~/.claude/skills/