hujjun/mcd-saver-strategist
麦当劳省钱点餐助手(麦门精算师)|麦当劳优惠券组合优化 Skill:拉取麦当劳菜单与全部可用优惠券,算出最省的点餐组合,巨无霸套餐 ¥47 → ¥21.9(省 53%)。McDonalds MCP(麦当劳 MCP)coupon optimizer · McDonalds China MCP Server · Agent Skill for WorkBuddy · 麦当劳程序员创意开发大赛参赛作品
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
麦当劳程序员创意开发大赛参赛作品 · 非麦当劳官方产品。 [](https://github.com/hujjun/mcd-saver-strategist/actions/workflows/ci.yml) 用户说"我想吃巨无霸套餐,怎么最便宜",它拉取门店菜单和所有可用优惠券, 用算法穷举出总价最低的合规组合,并帮你下单。 示例:巨无霸 + 中薯条 + 可乐,直选 ¥47.00; 用「1+1 随心配」组合后 ¥21.90,省 ¥25.10(53%)。 它不止会算"最便宜",还能回答四个衍生问题: 🎮 在线试算(无需登录): —— 优化算法的前端完整复刻,选好想吃的、切换目标、拖动预算和热量上限,实时算出最优组合; 页面里还有券体检和帕累托前沿图,打开即玩。 🔎 静态示例:docs/demo.html · 🖼️ 原理图:images/how-it-works.png · 🎬 宣传动画:images/promo.mp4 麦当劳的优惠是典型的组合爆炸问题: 本 Skill 的核心洞察是:取数交给 MCP,算术交给代码,表达交给 Agent。 (Windows 为 %USERPROFILE%\.workbuddy\skills\;MCP Token 配置见下文「安装」。) 前往麦当劳 MCP 开放平台 https://open.mcd.cn/mcp ,手机号登录后在「控制台」激活并复制 Token。 在 WorkBuddy 左侧边栏【专家·技能·连接器】→【连接器】→ 右上角【自定义连接器】→【配置 MCP】中, 填入 mcp-config.example.json 的内容, 并把 ${MCDMCPTOKEN} 替换为你的真实 Token(或用环境变量注入),保存后【启用】。 把 skills/mcd-saver-strategist/ 整个目录复制到 WorkBuddy 的用户技能目录: (Windows 为 %USERPROFILE%\.workbuddy\skills\) 装好后在对话框里直接说「我想吃巨无霸套餐,怎么点最便宜」即可触发。 示例 1 · 单人到店 精算师:拉菜单 + 四路券池 → 优化 → 「1+1 随心配 ¥12.9 覆盖巨无霸和中薯条,另外单点可乐 ¥9, 合计 ¥21.90,比直选省 ¥25.10」。 示例 2 · 预算硬约束 精算师:以 budget=30 求解,返回在预算内的最优搭配,并列出各方案到手价与热量。 示例 3 · 热量约束 精算师:引入 list-nutrition-foods,以 maxcalories=800 求解, 给出低卡又省钱的组合(如板烧鸡腿堡 + 麦咖啡 + 圆筒)。 示例 4 · 外送 精算师:delivery-query-addresses → delivery-query-stores → 后续流程同上, 下单前用 calculate-price 核价(含配送费)。 示例 5 · 券太多不会用 精算师:四路券池归一化 → auditcoupons() 逐张体检 → 「1+1 随心配值得用;这张'满 35 减 7'名义省 7 元,但用了它就吃不到 1+1,反而多花 18 元」。 示例 6 · 凑单 精算师:suggestgap() 用子集和 DP 找最小代价补位 → 「还差 7 元,加个香芋派 7.5…
Read the full README ↗ · Preview checked 2026-10-30T12:41:10.264Z
Inside the original README — Document outline
- 麦门省钱精算师 · mcd-saver-strategist
- 项目介绍
- 它解决什么问题
- 架构
- 一句话安装
- 安装
- 1. 申请麦当劳 MCP Token
- 2. 配置 MCP 连接
- 3. 安装本 Skill
- 使用示例
- 命令行快速体验(无需 Token)
- 真实性对照表
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: MIT. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
麦当劳省钱点餐助手(麦门精算师)|麦当劳优惠券组合优化 Skill:拉取麦当劳菜单与全部可用优惠券,算出最省的点餐组合,巨无霸套餐 ¥47 → ¥21.9(省 53%)。McDonalds MCP(麦当劳 MCP)coupon optimizer · McDonalds China MCP Server · Agent Skill for WorkBuddy · 麦当劳程序员创意开发大赛参赛作品
Repository facts
- Owner
- hujjun
- Primary language
- Python
- Stars
- 466
- Forks
- 5
- Open issues + pull requests
- 1
- License
- MIT
- Archived
- No
- Default branch
- main
- Created
- 2026-10-09T03:21:52.000Z
- Last push
- 2026-10-10T07:23:13.000Z
Topics and intended use
Owner-supplied topics: agent-skill, ai-agent, coupon-optimizer, coupons, deterministic-optimization, fast-food, mcd, mcdonalds, mcdonalds-mcp, mcp, mcp-server, money-saving, python, workbuddy, workbuddy-skill
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-16T12:08:52.409Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer