Mcd Mailu logo

Mcd Mailu

Community
calmsprite2001
mcd-mailu

麦途——麦当劳消费轨迹与场景叙事。当用户问「我的麦当劳账单」「我在麦当劳花了多少钱」「我最常点什么」「看看我的麦当劳足迹」「生成我的麦途卡片」时使用。基于麦当劳官方 MCP 读取历史订单,识别每单的场景(机场 / 赶早 / 深夜 / 连点 / 新店…),把订单讲成一个由数据支撑的故事,输出一张可截图分享的轨迹卡。只读不写:绝不创建、取消或修改任何订单。核心红线:卡片上的每一句话都必须能回溯到具体订单,绝不脑补数据里不存在的内容。

Overview

Publishercalmsprite2001
Repositorymcd-mailu
Skill namemcd-mailu
Stars
84
Forks
5
Bundled files
15
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.

  • 15 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by calmsprite2001 on GitHub. Read the source before you install it.

Installation

Install the Mcd Mailu 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/calmsprite2001/mcd-mailu/tree/main
  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/calmsprite2001/mcd-mailu.git \
  .claude/skills/mcd-mailu
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mcd Mailu 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 Mailu 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 Mailu 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.

麦途 · mcd-mailu

别的工具告诉你「该点什么」。麦途做的是相反的事——读懂你已经点的,把它讲成一个故事。

麦当劳订单里最被低估的字段是门店名和时间。店名里藏着「机场」「火车站」「医院」「写字楼」,时间里藏着早班机、深夜加班和周末遛娃。麦途把这些线索收集起来,识别场景,串成轨迹。

核心红线(违反即产品死亡):卡片上的每一句话,都必须能回溯到至少一条真实订单。数据里没有的东西,一个字都不能写。

什么时候用

  • 「我在麦当劳花了多少钱」「我最常点什么」
  • 「生成我的麦当劳年度账单 / 足迹」
  • 「看看我都在哪吃过麦当劳」

前置条件

环境变量 MCD_MCP_TOKEN(https://open.mcd.cn/mcp 手机号登录领取)。 没有 Token 时不要调用工具,引导领取,或提示 --demo 用内置样本看效果。

五步工作流

Step 1 · 拉单

  • order-list:餐食订单(一次返回全量,无分页参数,重度用户可能被服务端截断,属已知风险)
  • mall-order-list:商城订单(支持 lastId 翻页,按 hasNext 取完为止)
  • now-time-info:当前时间,所有「近 N 个月」表述的唯一基准

判据:

  • 商城订单(买卡、兑券)与餐费分开统计,不得混入消费额。
  • 工具失败就明说失败,不估算、不脑补。

Step 2 · 清洗归一

四条缺一不可:

  1. 状态过滤:只保留「订单已完成」,其余剔除并计数。
  2. 金额口径:realTotalAmount 为字符串、单位元,直接转 float。出现整数 ≥500 的量级异常时调 money.flag_suspicious 告警,人工核对,不自动换算。
  3. 去重:按 orderId 去重。
  4. 时间:createTime 是下单时间,用 money.parse_time 归一。时段统计一律用下单时间。

Step 3 · 场景识别

scene_engine.py 对每单打标签,规则透明可查、可扩展:

场景触发规则
出行慰藉店名含「机场 / 火车站 / 高铁 / GTC」
早班开场下单时间 05:00–10:30
深夜补给下单时间 21:00–05:00
一单多点同店 30 分钟内连续多单
新店打卡该门店首次出现
老地方同一门店第 3 次及以上

整单模式(画像层):

模式规则
天涯路人门店多样性 ≥0.8 且出行场景 ≥1 单
本地日常同店占比 ≥0.6
早餐型早餐场景占比 ≥0.5
深夜型深夜场景占比 ≥0.4

判据:

  • 规则全部写在 references/scene_rules.md,开源接受社区补充。这是本项目的护城河:词典越厚,认出的故事越多。
  • 每条规则命中必须记录依据(店名关键词、时间、订单号),供叙事层引用。

Step 4 · 叙事生成

narrative.py 用模板 + 数字生成文案,分两种模式:

  • 轨迹模式(样本 <10 单):不装统计。按时间顺序讲每一次,突出场景标签和连点细节。
  • 画像模式(样本 ≥10 单):统计结论,比率必须带分母。

判据:

  • 每个数字必须能指回订单号集合,写入 evidence。
  • 首屏结论是一句话,不是「分析报告」。范例:「11 个月里你只吃了 4 次麦当劳——4 次都在路上。」
  • 禁止形容词堆砌。「温暖」「治愈」这类词一行最多一个,且必须跟在数据后面,不许凭空抒情。
  • 禁止脑补品类偏好:数据里没有的餐品(如可乐),文案里不得出现。

Step 5 · 出卡片

card_render.py 生成单文件 HTML 轨迹卡。

判据:

  • 首屏是一条时间轴,不是柱状图。每单一个节点,节点带场景标签。4 单好看,80 单也好看。
  • 单文件、零外链、零 JS 依赖、断网可开,方便截图转发。
  • 卡片里不出现完整订单号、手机号、地址;门店名保留(它是故事的一部分)。
  • 页脚带免责与隐私说明。

红线

  1. 不做任何写操作:create-order、cancel-order、mall-create-order、party-order-create、draw-lottery 一律不碰。
  2. 订单明细不落盘,全部内存计算,输出只有聚合结果与场景标签。
  3. fixtures 全部是人工构造的假数据,绝不提交真实订单导出。
  4. Token 只从环境变量读,不打印、不进文件、不进日志。
  5. 不编造数字、不编造概率、不编造品类偏好。

文件

SKILL.md                   本文件
scripts/mcp_client.py      MCP 客户端(仅标准库)
scripts/probe.py           字段探测器(实测校准用)
scripts/money.py           金额/时间归一化
scripts/adapters.py        MCP 返回 → OrderRecord
scripts/scene_engine.py    场景标签与模式识别(规则驱动)
scripts/narrative.py       叙事生成(每句话带 evidence)
scripts/card_render.py     HTML 轨迹卡渲染
scripts/run.py             主流程,支持 --demo
scripts/gen_fixture.py     演示数据生成器
fixtures/demo_orders.json  人工构造的脱敏样本
references/scene_rules.md  场景识别词典(开源接受补充)
docs/index.html            离线演示页

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Mcd Mailu AI skill do?

麦途——麦当劳消费轨迹与场景叙事。当用户问「我的麦当劳账单」「我在麦当劳花了多少钱」「我最常点什么」「看看我的麦当劳足迹」「生成我的麦途卡片」时使用。基于麦当劳官方 MCP 读取历史订单,识别每单的场景(机场 / 赶早 / 深夜 / 连点 / 新店…),把订单讲成一个由数据支撑的故事,输出一张可截图分享的轨迹卡。只读不写:绝不创建、取消或修改任何订单。核心红线:卡片上的每一句话都必须能回溯到具体订单,绝不脑补数据里不存在的内容。

Why use Mcd Mailu on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/calmsprite2001/mcd-mailu/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Mcd Mailu?

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 Mailu?

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

Is the Mcd Mailu AI skill free?

It is published on GitHub by calmsprite2001. 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 👇