Token导航 LogoToken导航

Agent Skill · 开发

prototype(prototype 搜索)

prototype 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

prototype 是开发类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 19,716。

总安装 259周安装 11GitHub Stars 37下载 91核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:prototype(prototype 搜索)
来源仓库:https://github.com/simhacker/moollm
仓库路径:skills/prototype
安装命令:
npx skills add https://github.com/simhacker/moollm --skill prototype
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/simhacker/moollm --skill prototype

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

prototype 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态和协作事项进行整理。通过 npx skills add 命令从指定仓库安装并使用。

建议确认权限范围和维护状态,注意是否触发联网或文件操作。prototype 属于开发类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/prototype

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/simhacker/moollm --skill prototype;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

prototype 怎么安装?

在终端执行 npx skills add https://github.com/simhacker/moollm --skill prototype。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

prototype 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

prototype 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

prototype 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

prototype 用的人多吗?

公开数据是累计安装 259 次,近一周安装 11 次,下载 91 次,GitHub 37 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

prototype 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
prototype

prototype 搜索 · 本页

25937只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

PROTOTYPE

"Objects all the way down."

The philosophy of prototype-based inheritance: no classes, just concrete examples that you clone and modify.

Lineage: Self, this skill, and multiple parents

This skill is directly inspired by Self. In MOOLLM, Self is one of this skill’s prototypes: the schemapedia self mechanism names that parent lineage (Ungar, Smith, and collaborators). The same Delegation Object Protocol applies to skills as to room instances: an ordered PROTOTYPES.yml can list several parent skills—Self is not the only possible parent. Because prototype inherits from Self, it already follows the rules that let any MOOLLM object inherit from multiple prototypes (local wins, then each parent in order, first match wins).


The Problem with Classes

Classical inheritance says:

  1. Define an abstract blueprint (class)
  2. Instantiate it to create objects
  3. Objects are "instances of" classes

But this creates problems:

  • Abstraction gap: Classes describe things that don't exist
  • Rigidity: Class hierarchies are hard to change
  • Ceremony: Lots of boilerplate to create simple things

The Prototype Solution

Prototype-based inheritance says:

  1. Create a concrete example (prototype)
  2. Clone it to make new objects
  3. Modify the clone as needed
  4. Clones delegate to prototypes for missing slots

Everything is concrete. Everything exists.

Self as universal object machine

Self is a universal object machine: a minimal language of objects, slots, and delegation from which you can implement or host other object systems—classes (as conventions on top of prototypes), CLOS-style generic functions and method combination, generic dispatch lineages (ScriptX, Dylan, and related multimethod designs), COM / OLE / ActiveX-style component object models, PostScript Dictionary Stack NeWS "class.ps" Objects, JSON (maps of keys to values as object-shaped data), YAML Jazz (semantic comments beside the parsed tree in MOOLLM’s notation layer), and more. Those systems are not the same mechanism as Self; they are targets you model, embed, or bridge—Self and prototype delegation stay the bedrock.


How Self Works

Slots

Objects are collections of slots:

cat: (|
  name <- "Terpie".
  color <- "orange".
  meow = (| | "Meow!" |).
  parent* = catPrototype.
|)
  • name, color — data slots
  • meow — method slot
  • parent* — parent slot (for delegation)

Delegation

When you send a message to an object:

  1. Look in the object's own slots
  2. If not found, look in parent's slots
  3. Continue up the chain
  4. First match wins

Cloning

To create a new cat:

newCat := cat clone.
newCat name: "Stroopwafel".
newCat color: "tabby".

The new cat:

  • Has its own name and color slots
  • Delegates meow to the prototype
  • Can add new slots anytime

MOOLLM Implementation

MOOLLM implements prototype inheritance via the Delegation Object Protocol (DOP):

PROTOTYPES.yml

# In an instance directory
prototypes:
  - path: "skills/room"
  - path: "skills/adventure"

resolution:
  strategy: "first-match-wins"

File Resolution

  1. Check local directory
  2. Check each prototype in order
  3. First match wins
  4. State never inherits (always local)

Example: A Room Instance

examples/adventure-4/pub/
├── ROOM.yml           # Local override (shadows prototype)
├── PROTOTYPES.yml     # Points to skills/room
├── state/             # Local-only state
│   └── visitors.yml
└── (missing files delegate to skills/room/)

Why Prototypes for LLMs?

LLMs don't compute inheritance algorithms. They navigate files.

Prototype-based inheritance is LLM-friendly because:

  • Explicit: You can see the prototype chain
  • Navigable: Just follow file paths
  • Concrete: No abstract classes to imagine
  • Forgettable: Each lookup is independent

The Wisdom of Self

From the abstract of *Self: The Power of Simplicity* (Ungar & Smith, OOPSLA ’87):

*Self is an object-oriented language for exploratory programming based on a small number of simple and concrete ideas: prototypes, slots, and behavior.*

Source: Self bibliography · PDF

Self taught us that simplicity wins:

  • One mechanism (slots) instead of many
  • Objects are just dictionaries
  • Methods are just slots that happen to be code
  • Inheritance is just delegation

MOOLLM applies this: directories are objects, files are slots, resolution is delegation.


Historical Context

YearEvent
1986Ungar & Smith begin Self at Xerox PARC
1987Self paper published
1991Self 2.0 with compilation
1995JavaScript created (heavily Self-influenced)
2024MOOLLM applies Self to LLM filesystems

See Also


Further Reading

  • Ungar, D. & Smith, R. (1987). *Self: The Power of Simplicity* — bibliography, PDF
  • Smith, R. B. & Ungar, D. (1995). *Programming as an Experience: The Inspiration for Self* — bibliography, PDF
  • Ungar, D. (1995). *Organizing Programs Without Classes*
  • selflanguage.org
  • Curtis, P. (1997). *LambdaMOO Programmer's Manual* — HTML (objects, verbs, and the virtual reality as a programmable database)

平台分布

Codex

40.2%
按下载量换算37

Claude

30.34%
按下载量换算28

Cursor

18.11%
按下载量换算16

Gemini CLI

9.15%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills