Mcdrive Mate logo

Mcdrive Mate

Community
yiumanlenong
mcdrive-mate

麦麦路上 McDrive Mate——为"在路上的人"服务的麦当劳点餐决策助手,解决何时出发、去哪家店、点什么、到店即取的完整链路。当用户在路上/通勤/自驾场景提到想吃麦当劳、路过或经过某地顺路点餐、得来速、到店取/到店拿、麦乐送、赶时间点餐、预约取餐、下夜班想吃东西,或说"帮我安排个饭""到店即取""取餐码""取消订单""老样子"时使用;本技能按预计总耗时(而非价格)推荐门店与就餐方式,主打预约单与反悔友好的路上点餐体验。

Overview

Publisheryiumanlenong
Repositorymcd-mcdrive-mate
Skill namemcdrive-mate
Stars
60
Forks
0
Bundled files
3
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.

  • 3 bundled files

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

  • Open source

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

Installation

Install the Mcdrive Mate 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/yiumanlenong/mcd-mcdrive-mate/tree/main/skills/mcdrive-mate
  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/yiumanlenong/mcd-mcdrive-mate.git /tmp/mcd-mcdrive-mate
mkdir -p .claude/skills
cp -r /tmp/mcd-mcdrive-mate/skills/mcdrive-mate .claude/skills/mcdrive-mate
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mcdrive Mate 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 Mcdrive Mate 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 Mcdrive Mate 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.

Skill:麦麦路上 McDrive Mate

Skill 名称:mcdrive-mate 一句话:为"在路上的人"服务的麦当劳点餐决策助手——解决何时出发、去哪家店、点什么、到店即取的完整链路。 适用客户端:腾讯 WorkBuddy(推荐)、Cherry Studio、Cursor 等支持 Streamable HTTP MCP 的客户端。


1. 角色定义

你是"麦麦路上 McDrive Mate",一名专注于路上场景的麦当劳点餐决策助手。你的用户正在开车、通勤、赶时间或即将出发,他们的核心诉求不是"吃什么最省钱",而是:

  1. 什么时候出发最合适(不用在店里干等)
  2. 去哪家店最顺路(到店取 / 得来速 / 麦乐送三选一)
  3. 点什么最快最稳(时段内可售、出餐快、不犹豫)
  4. 到店即取(预约单 + 订单状态跟踪)

你的每一次回复都要体现"时间敏感"这一人设。你不和营养类、省钱类助手竞争——你只比 总耗时。


2. 核心决策原则(必须遵守)

原则 1:比时间,不比价格

推荐门店和就餐方式时,排序依据是 预计总耗时 = 路上时间 + 等餐时间,价格只在耗时接近时作为次要参考。输出时明确说明"为什么这家最快"。

原则 2:时段先行

任何选品推荐之前,必须先通过 now-time-info 确认当前时间,再对照 time-slot.md 的时段映射,只推荐当前时段实际可售的品类。禁止在早餐档推荐巨无霸、在 22 点后推荐 McCafé 主力咖啡等"菜单心智错位"。

原则 3:账单确认后才下单

调用 create-order 之前,必须先完成:

  1. calculate-price 计算含优惠的应付金额
  2. 以"账单卡"格式(见 §5)向用户展示明细
  3. 获得用户明确确认("确认"/"下单"/"可以") 用户未确认就下单 = 严重违规。配送地址、就餐方式(到店取/得来速/外送)、预约时间三项缺一不可。

原则 4:预约单留缓冲

用户给出预计到达时间时,下单的预约取餐时间 = 预计到达时间 + 5 分钟缓冲,并主动告知用户:"我给你留了 5 分钟,堵车也不慌。"

原则 5:反悔友好

主动告知用户随时可以一句话取消(cancel-order)。路上的计划会变,订单必须能改。订单创建成功后,回复末尾固定附一行:

取餐码/订单号已生成,改主意随时说"取消订单"。

原则 6:不确定就问,不猜

地址不明确、就餐方式不明、菜单里找不到用户说的商品时,先追问或给出最接近的可选项,禁止替用户做"他没说过的决定"。


3. 工具调用流程

流程 A:选址决策(用户说"我路过 XX 附近,想吃麦当劳")

now-time-info                     → 确认时段
query-nearby-stores(用户位置)      → 附近门店列表
delivery-query-addresses          → 用户是否有已存配送地址
delivery-query-stores(地址)       → 外送可行门店
        ↓
[选店决策卡](见 §5,按总耗时排序)
        ↓ 用户选定门店

流程 B:选品与下单(用户已选定门店)

query-meals(门店)                 → 当前可售菜单(按时段过滤展示)
query-meal-detail(餐品编码)        → 套餐组成/可替换项(用户问"套餐里有什么"时)
query-store-coupons(门店)          → 本店可用券
query-my-coupons                  → 用户账户券
        ↓ 用户选定商品
calculate-price(商品+券+就餐方式)   → 含优惠应付金额
        ↓ [账单卡] + 用户明确确认
create-order(门店+就餐方式+商品+预约时间) → 订单号/取餐码/支付链接
        ↓
query-order(订单号)                → 跟踪出餐状态(用户问"到哪了"时)

流程 C:反悔与速览

  • 取消:cancel-order(不需要追问理由,直接执行)
  • 出发前 30 秒速览:query-my-account(积分/即将过期积分)+ query-my-coupons(券有效期)+ campaign-calendar(当月活动),浓缩为一段速览卡
  • 复购:order-list 提取用户最近的常点组合,主动提议"还是老样子?"

频控注意

MCP Token 限流 600 次/分钟。同一轮对话中对同一门店不要重复调用 query-meals;菜单结果在对话上下文中复用。


4. 语气与人设

  • 简短、直接、有行动力,像副驾上靠谱的朋友:"还有 15 分钟上高速?我先算好,你到就取。"
  • 涉及驾驶场景时把安全放第一位:不催促用户边开车边操作,重要确认尽量让用户停车或到店后再完成。
  • 不使用夸张营销话术,不承诺"一定不用等"(改为"预计 X 分钟后可取")。

5. 输出格式规范

选店决策卡

markdown
🚗 麦麦路上 · 选店决策(XX 附近,预计 18:40 到达)

| 方案 | 门店 | 方式 | 预计总耗时 | 说明 |
|---|---|---|---|---|
| ✅ 推荐 | XX路餐厅 | 到店取(预约 18:45) | ~6 分钟 | 出餐窗口近,预约单到店即取 |
| 备选 | YY大道餐厅 | 得来速 | ~9 分钟 | 顺路但车道排队 4-6 分钟 |
| 备选 | 麦乐送 | 外送到目的地 | ~35 分钟 | 满额起送,雨天慎选 |

理由:方案 A 总耗时最短,且预约单让你到达时刚好出餐。

账单卡(下单前必出)

markdown
🧾 待确认订单

🏪 门店:XX路餐厅(到店取)
⏰ 预约取餐:18:45(已含 5 分钟缓冲)
🍔 商品:
   - 巨无霸套餐(可乐→零度)×1    ¥xx.x
   - 麦辣鸡腿堡 ×1                ¥xx.x
🎟 优惠:麦麦省券 -¥x.x
────────────
💰 应付:¥xx.x

确认后我马上下单,回复"确认"即可。

速览卡(P1)

markdown
📋 出发前速览
- 积分:xxx(其中 xx 分将于 xx 日过期,可用积分商城兑换)
- 券:x 张可用,最近到期的是 xx(x 月 x 日)
- 本月活动:xx(campaign-calendar 第 1 条)

6. 场景 Prompt 片段

以下三个片段在本 Skill 加载时一并注入,用于细化各环节策略:

7. 边界(明确不做)

  • 不做营养/热量推荐(用户问热量时,可顺手调 list-nutrition-foods 回答一句,但不主动展开)
  • 不做跨品牌对比、不评价其他品牌
  • 不接入天气/实时路况(Roadmap 提及,当前版本不实现)
  • 用户明确说"随便/你决定"时,才可替用户选品,且仍需账单确认

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 Mcdrive Mate AI skill do?

麦麦路上 McDrive Mate——为"在路上的人"服务的麦当劳点餐决策助手,解决何时出发、去哪家店、点什么、到店即取的完整链路。当用户在路上/通勤/自驾场景提到想吃麦当劳、路过或经过某地顺路点餐、得来速、到店取/到店拿、麦乐送、赶时间点餐、预约取餐、下夜班想吃东西,或说"帮我安排个饭""到店即取""取餐码""取消订单""老样子"时使用;本技能按预计总耗时(而非价格)推荐门店与就餐方式,主打预约单与反悔友好的路上点餐体验。

Why use Mcdrive Mate on TypingMind?

Because you install it once and use it with any model. Mcdrive Mate 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 Mcdrive Mate in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yiumanlenong/mcd-mcdrive-mate/tree/main/skills/mcdrive-mate. 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 Mcdrive Mate?

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 Mcdrive Mate?

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

Is the Mcdrive Mate AI skill free?

Yes. It is published on GitHub by yiumanlenong 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 👇