Mcd Menu Stage logo

Mcd Menu Stage

Community
ddouworld
mcd-menu-stage

根据用户预算、人数和饮食偏好,先通过麦当劳 MCP 领取所有当前可领优惠券,再查询门店可用券、可售餐品并核价,生成带剪影猜谜和登场揭晓的可分享 HTML 菜单。适用于麦当劳选餐与菜单展示请求。

Overview

Publisherddouworld
Repositorymcd-menu-stage
Skill namemcd-menu-stage
Stars
87
Forks
0
Bundled files
17
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.

  • 17 bundled files

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

  • Open source

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

Installation

Install the Mcd Menu Stage 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/ddouworld/mcd-menu-stage/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/ddouworld/mcd-menu-stage.git \
  .claude/skills/mcd-menu-stage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mcd Menu Stage 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 Menu Stage 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 Menu Stage 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.

麦麦出场图鉴

先领取所有当前可领优惠券,再把用户的麦当劳用餐需求变成一份真实可用的推荐菜单,用固定 HTML 模板逐个揭晓餐品。每次更换菜单 JSON,不重写模板。没有匹配餐品时也生成 HTML,在页面内说明原因和调整建议。

客户端交付规则

  • 对应客户端最终只交付生成的 HTML 附件,或一条可点击的 HTML 文件链接。不在对话中列出推荐餐品、价格、套餐组成、推荐理由或预算不足的解释,不粘贴 HTML 源码。
  • 需求不完整时可以在生成前进行必要补问,不能先在对话里曝光候选或推荐物品。执行进度只描述处理步骤。
  • 推荐成功、待核价和预算不足的原因、金额及建议都写进 HTML。生成后不要追加文字总结或重复菜单。
  • 根据运行环境识别客户端名,填入 clientName,例如确实在 WorkBuddy 运行时填 WorkBuddy。环境不提供可靠名称时使用「当前客户端」,不猜测、不为此额外追问。
  • 页面可以提示用户回到该客户端,并提供可复制的调整需求。不能自行给客户端发送新消息、修改预算或自动开启新一轮推荐。
  • 客户端交付 HTML;页面内的导出按钮只导出 PNG 海报,不导出 HTML。PNG 展示完整菜单与预算,或无匹配结果与客户端调整提示,离线生成。

选餐与数据查询

  • 提取预算(包含整单费用)、人数、口味、忌口、用餐方式。只补问会影响选餐或报价的信息;默认预算是整单总预算,含配送费。
  • 每次新的真实推荐流程先调用 auto-bind-coupons,领取麦麦省所有当前可领优惠券,不根据本次想吃的菜品预先挑券,也不凭空指定 couponId。参数以当前工具 schema 为准。只有调用成功或服务明确返回无券可领,才进入后续选餐;领取失败、部分失败或结果不明时,先说明并处理失败,不跳过这一步,不盲目重复领取。已领取的券、领取数量均以真实返回为准。
  • 使用用户选择的门店;没有门店时询问大致位置,通过 query-nearby-stores 查询,到店堂食 / 外带需选择合适的用餐方式。外送时按服务工具要求用 delivery-query-stores 查询可配送门店。只读已有地址时可用 delivery-query-addresses;导出时不保留地址。
  • 领取完成并确定门店后,必须调用 query-store-coupons,查询当前门店和用餐方式实际可使用的优惠券,再选餐。领取成功不等于该券适用于当前门店、时段或餐品;需要账户券信息时可补充 query-my-coupons,但不能替代门店可用券查询。
  • 从实际 MCP query-meals 返回的可售菜单选餐,用 query-meal-detail 核实套餐组成、可替换项及与需求相关的信息。工具参数以当前服务提供的 schema 为准,不猜测参数名或餐品编码。
  • 需要营养数据时调用 list-nutrition-foods,只能引用对应餐品及规格确实返回的数据;缺失信息写明未知。不能凭口味名称保证无过敏原。
  • 筛选满足用户明确限制的候选组合,兼顾人数、用户偏好及用餐场景,再调用 calculate-price 核验所选门店、餐品规格、数量、用餐方式、优惠和整单费用。不可自行叠加优惠或用单品价格猜测套餐价。
  • 有有效报价且总价不超过预算时,输出 quote.status: verified。更换任何餐品、数量、门店、优惠或用餐方式后必须重新核价。
  • 无法取得有效报价时,可输出 quote.status: unknown 的待核价页面,所有金额及单价写为 null,明确不能保证满足预算。没有符合当前预算和需求的餐品时,输出 result.status: no-match、items: []、quote.status: not-applicable 的结果页面,原因写入 result.message,不在对话里解释或等待用户调高预算才生成 HTML。
  • 预算不足只是本轮查询结论,不能按 1 元等固定阈值判断;检查领取后的可用优惠,实际可能存在免费或低价方案。result.minimumTotal 只有在真实核验候选方案报价后才填写,否则设为 null,页面不编造起价或差额。需求或供应导致无匹配时使用对应 reason,不把查询故障当作预算不足。
  • MCP 不可用或未配置时,说明需要接入麦当劳 MCP;只有用户选择演示时才用示例数据,不把示例标为实际查询。

领券是推荐流程的前置步骤。该流程不包含下单、积分兑换或购买付费权益。离线演示、PNG 导出和重播出场不调用 MCP;同一轮已成功领券后的改菜或重新核价无需再次领券,但更换门店或用餐方式需要重新查询可用券。

生成页面

  1. 按 菜单数据格式 组装 data/menu.json。sourceTools 按本轮首次实际调用顺序记录工具名,真实菜单必须包含先领券、再查门店券、后查菜单的记录;仅填工具名不能证明调用成功。仅保留展示所需的字段,不能把完整 MCP 响应或原始用户地址放进 JSON。

  2. 有匹配菜单时,为每个餐品写 1–3 条由宽到窄的提示、我就是——{餐品名称}! 的揭晓台词及具体推荐理由。无匹配时使用空数组,按 1 元预算示例 填写结果状态和客户端提示,不展示或暗中推荐超预算餐品。事实来自查询结果;文案可以活泼,不编造促销、价格、营养信息或官方背书。

  3. 有合法可用的餐品图片时,提供本地 PNG / JPEG / WebP 的 imageFile;脚本会嵌入 HTML。没有图片则按餐品类别设置 art,使用模板内的原创示意插画。猜谜玩法使用原创舞台,不使用宝可梦角色、标志、素材或原作音频。

  4. 在 Skill 根目录执行:

    sh
    node scripts/render-menu.mjs --data data/menu.json --out outputs/menu.html
  5. 若校验失败,修正对应数据;预算冲突时重新选餐与核价,确实无匹配则生成无匹配状态的 HTML。生成成功后,对话仅交付 HTML 附件或文件链接。输出是一份可离线打开的 HTML;推荐成功时默认音效关闭,用户可揭晓、集结菜单、重播、导出 PNG 或打印;无匹配时可导出 PNG 结果或复制调整需求。

演示

用户希望先看效果时执行:

sh
node scripts/render-menu.mjs --data data/menu.example.json --out outputs/demo.html

示例餐品、价格和优惠只用于展示交互。实际接入方式及核验状态见 MCP_INTEGRATION.md。

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 Menu Stage AI skill do?

根据用户预算、人数和饮食偏好,先通过麦当劳 MCP 领取所有当前可领优惠券,再查询门店可用券、可售餐品并核价,生成带剪影猜谜和登场揭晓的可分享 HTML 菜单。适用于麦当劳选餐与菜单展示请求。

Why use Mcd Menu Stage on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ddouworld/mcd-menu-stage/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 Menu Stage?

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 Menu Stage?

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

Is the Mcd Menu Stage AI skill free?

It is published on GitHub by ddouworld. 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 👇