Mcd Desktop Pet logo

Mcd Desktop Pet

Community
kv-chiu
mcd-desktop-pet

便利贴桌面宠物标准化 CLI 与 AI Agent 技能包。通过标准 CLI 指令 (mcd-desktop-pet) 操控桌面宠物并进行便利贴备忘的增删改查、归档出餐与贴回桌面。所有 CLI 命令默认输出纯 JSON 格式,供 AI Agent 直接精准解析。

Overview

Publisherkv-chiu
Repositorymcd-desktop-pet
Skill namemcd-desktop-pet
Stars
144
Forks
3
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by kv-chiu on GitHub. Read the source before you install it.

Installation

Install the Mcd Desktop Pet AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/kv-chiu/mcd-desktop-pet/tree/main/skill
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/kv-chiu/mcd-desktop-pet.git /tmp/mcd-desktop-pet
mkdir -p .claude/skills
cp -r /tmp/mcd-desktop-pet/skill .claude/skills/mcd-desktop-pet
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mcd Desktop Pet in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mcd Desktop Pet on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mcd Desktop Pet is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

便利贴桌面宠物 Agent 技能规范 (mcd-desktop-pet)

本技能赋予 AI Agent(Claude Code、Cursor、Antigravity、Codex 等)通过标准化统一命令行工具 (mcd-desktop-pet) 操控本地桌面宠物与管理桌面便利贴系统的能力。


一、 核心交互规范

  1. 统一小写命令行:CLI 命令严格采用全小写 mcd-desktop-pet(Windows 下为 mcd-desktop-pet.exe 或 mcd-desktop-pet.cmd),无任何短别名,保持标志唯一确定。
  2. 默认 JSON 输出:所有 CLI 命令的结果均默认输出为纯 JSON,标准输出(stdout)严格保留给 JSON 结果,诊断日志统一输出至标准错误(stderr)。AI Agent 无需追加 --json 即可直接解析。
  3. 确定性退出码:
    • 成功:退出码为 0,标准输出输出有效 JSON 对象或数组。
    • 失败:非零退出码,标准输出输出统一错误结构 {"error": "错误原因说明"}。
  4. 统一入口与复用:无参数运行主程序严格等同于 mcd-desktop-pet start。若服务或桌宠已在运行中,start 会自动复用已有实例,避免重复创建。

二、 自然语言意图到 CLI 命令映射表

1. 便利贴生命周期管理 (Note Operations)

用户自然语言意图标准 CLI 命令说明与返回结构
“帮我记一张便签:明天下午 3 点开会”mcd-desktop-pet note create --text "明天下午 3 点开会"创建便签,返回 {"id": "note_xxx", "summary": "...", "status": "active"}
“新建带标题便签:待办事项”mcd-desktop-pet note create --title "待办" --text "买麦辣鸡腿堡"创建带标题便签
“列出当前桌面上的活动便签”mcd-desktop-pet note list --status active返回当前悬浮在桌面上的便签列表 [{"id": "...", "summary": "...", "status": "active"}]
“查看已经归档出餐的历史便签”mcd-desktop-pet note list --status archived返回已出餐/归档的历史便签列表
“查看全部便签(含活动与归档)”mcd-desktop-pet note list --status all返回所有便签清单
“把这条便签归档(标记完成/出餐)”mcd-desktop-pet note archive <id>标记归档出餐,桌宠端将触发印章砸印动效并收起,返回归档后状态
“把这张历史便签重新贴回桌面”mcd-desktop-pet note restore <id>从便签盒恢复并贴回桌面,重新在桌面悬浮展示
“彻底删除这张便签”mcd-desktop-pet note delete <id>彻底删除便签数据,返回 {"id": "note_xxx", "deleted": true}

2. 系统生命周期与控制台 (System & Web)

用户自然语言意图标准 CLI 命令说明与行为
“启动桌面宠物”mcd-desktop-pet start统一启动中枢服务与桌宠客户端;若已运行则直接复用
“停止 / 退出桌面宠物”mcd-desktop-pet stop优雅停止中枢服务与桌宠表现层进程,清理 PID 锁
“检查桌宠和服务当前运行状态”mcd-desktop-pet status返回 {"server_running": bool, "pet_running": bool, "port": 23301, "theme": "mcdonalds"}
“打开历史便签盒 / 管理控制台”mcd-desktop-pet web按需启动:若服务未启动会自动在后台拉起服务(无需启动桌宠),并在浏览器打开全屏瀑布流大屏

三、 Agent 场景演练与调用范式

场景 1:用户让 Agent 记录灵感或待办

用户输入:“帮我记一张便签:周五前要完成文档评审” Agent 执行:

bash
mcd-desktop-pet note create --text "周五前要完成文档评审"

CLI 输出 (stdout):

json
{
  "id": "note_5fa21d9b",
  "summary": "周五前要完成文档评审",
  "status": "active"
}

Agent 回复:“已经帮您在桌面上贴好新便签:‘周五前要完成文档评审’(流水号 note_5fa21d9b)📝✨”


场景 2:用户让 Agent 查看当前便签并归档完成项

用户输入:“看看我桌面上有什么便签,把刚才评审文档的那张归档了” Agent 执行 1:

bash
mcd-desktop-pet note list --status active

CLI 输出 1:

json
[
  {
    "id": "note_5fa21d9b",
    "summary": "周五前要完成文档评审",
    "status": "active"
  }
]

Agent 执行 2:

bash
mcd-desktop-pet note archive note_5fa21d9b

CLI 输出 2:

json
{
  "id": "note_5fa21d9b",
  "summary": "周五前要完成文档评审",
  "status": "archived"
}

Agent 回复:“查找到桌面上有一张便签‘周五前要完成文档评审’,已为您盖章出餐并安全归档至历史便签盒!🍟✓”


场景 3:快速检查运行状态与打开大屏

用户输入:“桌宠还在跑吗?帮我打开便签大屏” Agent 执行 1:

bash
mcd-desktop-pet status

Agent 执行 2:

bash
mcd-desktop-pet web

Agent 回复:“当前中枢服务正常运行中。已在您的浏览器中打开历史便签盒大屏,您可以在瀑布流中浏览所有历史备忘与出餐记录!🌐”


四、 交付形态与直接调用指引 (Delivery & Invocation)

本项目交付物为完全自包含的独立预编译二进制与应用包,无需执行任何安装、配置或卸载脚本,下载即用:

  • macOS:交付单应用包 mcd-desktop-pet.app。双击直接启动桌宠;AI Agent 或终端可直接带参数调用包内主程序:

    bash
    # 直接调用应用包内主程序(默认输出 JSON)
    /Applications/mcd-desktop-pet.app/Contents/MacOS/mcd-desktop-pet note create --text "待办事项"
    /Applications/mcd-desktop-pet.app/Contents/MacOS/mcd-desktop-pet note list --status active
    /Applications/mcd-desktop-pet.app/Contents/MacOS/mcd-desktop-pet status

    (若已将应用包主程序创建符号链接至 /usr/local/bin 或系统 PATH,可简写为 mcd-desktop-pet)

  • Windows:交付单可执行文件 mcd-desktop-pet.exe。双击直接启动桌宠;AI Agent 或终端可直接在命令行调用:

    powershell
    # 直接调用可执行文件(默认输出 JSON)
    .\mcd-desktop-pet.exe note create --text "待办事项"
    .\mcd-desktop-pet.exe note list --status active
    .\mcd-desktop-pet.exe status

五、 错误处理与规范约定

  1. 退出码机制:所有命令成功时返回退出码 0,失败时返回非零退出码。
  2. 错误响应格式:当命令执行遇到错误时,标准输出均返回标准的 JSON 错误结构,便于 Agent 准确捕获:
    json
    {
      "error": "note not found: note_xxx"
    }
  3. 静默与纯粹性:Go 主程序在 CLI 模式下,标准输出(stdout)严格保留给机器可解析的 JSON 结果,任何运维诊断日志统一打到标准错误(stderr),AI Agent 可直接使用 JSON.parse() 解析结果。

Frequently asked questions

What does the Mcd Desktop Pet AI skill do?

便利贴桌面宠物标准化 CLI 与 AI Agent 技能包。通过标准 CLI 指令 (mcd-desktop-pet) 操控桌面宠物并进行便利贴备忘的增删改查、归档出餐与贴回桌面。所有 CLI 命令默认输出纯 JSON 格式,供 AI Agent 直接精准解析。

Why use Mcd Desktop Pet on TypingMind?

Because you install it once and use it with any model. Mcd Desktop Pet is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mcd Desktop Pet in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kv-chiu/mcd-desktop-pet/tree/main/skill. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Mcd Desktop Pet?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mcd Desktop Pet?

As many as you like. As long as a model supports skills, you can use Mcd Desktop Pet with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mcd Desktop Pet AI skill free?

Yes. It is published on GitHub by kv-chiu under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇