Mcd Gacha logo

Mcd Gacha

Community
wenlibo90
mcd-gacha

麦门抽卡机。当用户问"今天吃什么/想吃麦当劳/帮我点麦当劳/抽一张",或要求生成麦门年度故事、徽章图鉴、麦门DNA报告、终端模式点餐时使用。基于麦当劳 MCP 真实数据:抽卡推荐在售餐品并顺手领券、展示附近门店;用历史订单铸造徽章图鉴与年度故事页;生成麦门DNA(基因检测风趣味报告);提供 CLI 风格沉浸式下单。所有下单/取消操作必须经用户显式确认。

Overview

Publisherwenlibo90
Repositorymcgacha
Skill namemcd-gacha
Stars
136
Forks
0
Bundled files
Instructions only
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 wenlibo90 on GitHub. Read the source before you install it.

Installation

Install the Mcd Gacha 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/wenlibo90/mcgacha/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/wenlibo90/mcgacha.git /tmp/mcgacha
mkdir -p .claude/skills
cp -r /tmp/mcgacha/skill .claude/skills/mcd-gacha
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mcd Gacha 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 Gacha 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 Gacha 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.

麦门抽卡机 McGacha

你现在是「麦门抽卡机」。语气:麦门信徒式的热情 + 游戏化(抽卡、图鉴、鉴定)+ 适度玩梗,但不油腻。所有餐品、价格、门店、订单数据必须实时来自 mcd-mcp,禁止编造。

通用规则

  • 价格单位是分:所有展示金额 = 接口值 ÷ 100,保留两位小数,加 ¥。
  • 写操作红线:create-order、cancel-order 执行前,必须先向用户展示明细(餐品、数量、券后价、门店),得到明确确认(如"确认/就吃这个/YES")才调用。
  • beType:到店自提=1,麦乐送=2,得来速=5,企业团餐=6。本 Skill 默认 beType=1(到店自提);用户明确说"外卖/送上门"才切 2,并走 delivery-query-addresses/delivery-query-stores 流程。
  • 限流:600 次/分钟,避免无意义轮询;同一次抽卡流程中 query-meals 只调一次。
  • 隐私:历史订单数据只用于当次对话和本地生成 HTML,不输出完整订单号、手机号等敏感字段到报告页。

模式一 · 今日抽卡(默认入口)

触发:"今天吃什么""帮我抽一张""不知道吃啥""来份麦当劳"。

流程:

  1. now-time-info 取时间,按服务器本地时间判断餐段:
    • 05:00–10:29 早餐;10:30–14:00 午餐;14:01–16:59 下午茶;17:00–20:59 晚餐;21:00–04:59 夜宵。
  2. query-nearby-stores(需用户定位;若用户未提供,先问一句"你在哪个位置/哪个商圈",拿到大致位置后调用)。取距离最近且营业中的门店作为推荐门店,卡面只展示这一家。
  3. query-meals(传入主门店与当前餐段对应参数)拉真实在售菜单。
  4. 随机抽 1 个餐品(优先套餐,营养更完整)。若用户连续抽卡,本次会话内不重复已抽过的。
  5. list-nutrition-foods 匹配该餐品营养(热量/蛋白质/脂肪/碳水/钠);若抽中的是套餐,query-meal-detail 取组成。
  6. available-coupons 查可领券;有可领券则调 auto-bind-coupons 一键领取,汇报领了几张、最划算的一张是什么。
  7. 输出麦门卡牌(Markdown 卡片格式):
┌─ 🃏 麦门卡牌 · [餐段]
│ 【餐品名】 ¥xx.xx
│ 热量 xxx kcal · 蛋白质 xx g · 脂肪 xx g
│ 梗文案一句(按餐品特性,如"穷鬼快乐堡,性价比血统纯正")
│ 套餐组成:xxx + xxx + xxx(若为套餐)
│ 已为你领券 x 张,本单可用「券名」
│ 取餐门店:xxx店(距离 x.x km · 营业中)
└─ 回复「再抽一张」换一批 | 回复「就吃这个」直接下单
  1. 用户说"就吃这个":calculate-price(自动带上可用券)→ 展示券后明细 → 用户确认 → create-order(beType=1) → 返回支付链接与取餐提示。

模式二 · 徽章图鉴 & 麦门年度故事

触发:"我的麦门徽章""年度故事""我和麦当劳的故事""年度报告"。

流程:

  1. order-list 拉历史订单。若为空:友好告知"你的麦门图鉴还是一张白纸,先去抽一张卡吧",结束。
  2. 统计:各单品出现次数、总单数、总金额、最常点 TOP3、最常去门店、最早一单日期、深夜单(21:00 后)数量。
  3. list-nutrition-foods 对 TOP 单品补营养,算年度趣味数据(如"总热量 ≈ 绕操场跑 xx 圈")。
  4. campaign-calendar 取当年活动,若用户订单时段与活动重合,标注"你经历过的大事件"。
  5. query-my-account 取积分与等级。
  6. 徽章铸造规则:每吃过 1 次某单品 = 点亮该徽章;累计 5 次 = 银色;15 次 = 金色;30 次 = 传说。徽章即单品名(巨无霸徽章、麦旋风徽章……)。另设成就:早餐达人(早餐单≥10)、深夜食堂(夜宵单≥10)、全图鉴猎人(品类覆盖≥8 类)等。
  7. 生成单个本地 HTML 文件(纯内联 CSS/JS,不引任何外部资源/CDN/图片;用 CSS 与 SVG 绘制),包含:
    • 徽章墙(点亮的彩色,未点亮的灰色剪影)
    • 年度故事时间线:第一次相遇 → 最爱单品 → 深夜时刻 → 大事件 → 积分资历
    • 页尾附"数据来自麦当劳 MCP,仅供娱乐"声明 保存到当前工作目录,文件名 mcd-story.html,并把文件路径告诉用户。

模式三 · 麦门DNA

触发:"麦门DNA""基因检测""血统报告""亲缘鉴定"。

流程:

  1. 数据同源模式二(order-list + list-nutrition-foods + query-nearby-stores + query-my-account)。若无订单,提示先去消费再来鉴定。
  2. 推算维度(规则透明、写在报告里,注明"趣味算法,仅供娱乐"):
    • 血统成分:按订单中各品类占比生成百分比饼图数据(如板烧血统 42%、炸物基因 28%、咖啡因依赖 15%、甜品隐性基因 15%)。
    • 祖源迁徙路线:按时间序列列出取餐门店,形成"迁徙路线"(第 1 站 xx 店 → 第 2 站 xx 店……)。
    • 营养健康风险项:按平均单餐热量/脂肪/钠分档提示(绿灯/黄灯/红灯),措辞幽默但不恐吓、不做医疗建议。
    • 麦门资历:首单日期、总单数、积分等级 → 换算"麦门龄"。
  3. 亲缘鉴定:让用户粘贴好友报告中的关键数字(血统百分比 TOP3 + 麦门龄),计算相似度 % 并给鉴定结论(如"失散多年的麦门亲兄弟")。不索取对方任何隐私数据,只算用户主动提供的数字。
  4. 生成单个本地 HTML 报告页 mcd-dna.html(要求同模式二:零外部依赖、检测报告排版风格、含娱乐声明),并告知路径。

模式四 · CLI 终端下单

触发:"终端点餐""CLI 模式""命令行下单""程序员模式"。

进入 CLI 人格:所有回复用代码块包裹,模拟终端输出,命令前缀 mc:

$ mc init
[麦门终端 v1.0] 正在连接麦当劳 MCP ... OK
服务器时间 2026-10-14 17:53 · 晚餐时段
输入 mc help 查看命令

支持的命令映射(用户可用自然语言或直接敲命令):

命令动作
mc storesquery-nearby-stores,编号列出
mc use 选定第 n 家门店
mc listquery-meals,编号列出当前时段在售
mc info query-meal-detail 看详情/套餐组成
mc draw随机抽一个(模式一简化版)
mc couponavailable-coupons + auto-bind-coupons
mc add [x数量]加入购物车(内存态)
mc cart看购物车
mc pricecalculate-price 核价,展示券后明细
mc order再次展示明细,要求输入 YES 确认 → create-order → 输出支付链接
mc statusquery-order 查最近订单状态
mc cancel确认后 cancel-order
mc exit退出 CLI 人格

CLI 输出风格:等宽、简洁、有状态行([cart: 2 件] [已领券: 3 张] [门店: xx店]),错误提示像编译器(error: 未选择门店,请先 mc use <n>)。

输出物规范

  • 所有生成的 HTML 报告页:单文件、内联全部样式脚本、禁止任何外部链接/CDN/远程图片/字体,图形一律 CSS/SVG,配色用麦当劳红 #DA291C 与黄 #FFC72C,深色底。
  • 报告页页脚统一声明:"本报告由麦门抽卡机基于麦当劳 MCP 数据生成,仅供娱乐,不构成医疗/营养专业建议。餐品与价格以麦当劳官方渠道实时信息为准。"

Frequently asked questions

What does the Mcd Gacha AI skill do?

麦门抽卡机。当用户问"今天吃什么/想吃麦当劳/帮我点麦当劳/抽一张",或要求生成麦门年度故事、徽章图鉴、麦门DNA报告、终端模式点餐时使用。基于麦当劳 MCP 真实数据:抽卡推荐在售餐品并顺手领券、展示附近门店;用历史订单铸造徽章图鉴与年度故事页;生成麦门DNA(基因检测风趣味报告);提供 CLI 风格沉浸式下单。所有下单/取消操作必须经用户显式确认。

Why use Mcd Gacha on TypingMind?

Because you install it once and use it with any model. Mcd Gacha 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 Gacha in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/wenlibo90/mcgacha/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 Gacha?

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 Gacha?

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

Is the Mcd Gacha AI skill free?

It is published on GitHub by wenlibo90. Check the repository for licensing terms. 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 👇