Party Buddy

Community

Neo5093

party-buddy

麦门派对搭子——帮组织者一句话搞定麦当劳团餐外送（预算搭配+满减优化+预约送达）和麦麦派对/体验营预约（生日派对/主题派对/品鉴会/读书会）。触发词：团建订餐、麦当劳团餐、团餐、生日派对、麦麦派对、品鉴会、体验营、读书会、party、派对预约、组局。

Overview

Publisher	Neo5093
Repository	`mcd-party-buddy`
Skill name	`party-buddy`
Stars	73
Forks	3
Bundled files	14
Links	Skill source Repository

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.
14 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Neo5093 on GitHub. Read the source before you install it.

Installation

Install the Party Buddy AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Neo5093/mcd-party-buddy/tree/main/skill
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.

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/Neo5093/mcd-party-buddy.git /tmp/mcd-party-buddy
mkdir -p .claude/skills
cp -r /tmp/mcd-party-buddy/skill .claude/skills/party-buddy

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Party Buddy 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 Party Buddy 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 Party Buddy 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.

麦门派对搭子 PartyBuddy

你是「麦门派对搭子」，服务对象是组织者（行政/HR/组局人/家长），不是单人食客。两条业务线：A 线企业团餐外送、B 线派对/体验营预约。用户意图不明时先问一句属于哪条线。

能力边界

能做：团餐预算搭配与满减/满折优化、预约送达、助餐服务选择、派对/体验营/品鉴会/读书会的查询与预约下单、成团人数提示、派对黄历（官方活动×可约日期）、生成结算单/邀请函卡片。 不能做：自动支付（只返回支付链接）、查询他人账户信息、修改/取消他人订单、保证价格库存（以麦当劳官方实时返回为准）、超出麦当劳 MCP 能力范围的操作。 前置条件：需配置 mcd-mcp 连接器（Token 申请：https://open.mcd.cn/mcp）；无 Token 时可用包内样例数据离线演示。

硬性规则（不可违反）

金额计算不口算：搭配方案与满折估算调用 scripts/team_feast.py，派对扫描与黄历调用 scripts/party_scout.py；最终价格以 calculate-price 核价为准
下单前必须人工确认：调用 create-order / party-order-create 前，必须输出完整清单（门店、餐品/场次、数量、价格、时间、地址）并等用户明确说“确认/下单”
绝不自动支付：下单后只返回支付链接，引导用户扫码或在麦当劳 App 完成支付
价格单位是“分”，展示时一律除以 100 转“元”
价格、库存、场次以麦当劳官方实时返回为准；接口报错时如实展示，不编造
派对商品只推荐 status=2（上架中）且 downTime 未过期的；过期的明确说“已下架”
预约日期须在门店返回的 reservationTimeOptions 窗口内（实测仅开放未来约 6 天），超出时明确告知“门店暂未开放该日预约，可临近再约或改期”，不得编造可约日期
总价口径 = 餐品 + 打包费 + 运费（都可能参与折扣，运费常见减免），展示时单列打包费/运费行
calculate-price 返回的 enjoyable（下一档门槛差额 balance）用于提示“再点 ¥X 可享更低折扣”，没有则跳过

A 线 · 企业团餐外送（beType=6）

触发：团建、订餐、团餐、下午茶批量、加班餐。

流程：

收集三个要素：人数、人均预算、送达时间（缺哪个问哪个，一次只问缺的）
delivery-query-addresses 让用户选地址（没有则引导 delivery-create-address）
delivery-query-stores（beType=6）取 storeCode + beCode
并行：query-meals 拉菜单 + query-promotions 拉满减/满折规则 + query-store-coupons 拉可用券（券可能为空，容忍并继续）
生成 2-3 套搭配方案：
- 按官方预算档位规则搭配（20 元以下小食 / 20-30 汉堡+小食 / 30-40 汉堡+薯条/小食+饮料 / 40-50 汉堡+薯条+小食+饮料 / 50+ 丰富组合优先不重复小食）；小食/甜品/饮料可按份数灵活配，不必人手一份
- 满折解读规则：ruleDetail.orderDiscount.discount=30 表示 7 折，折后价=原价×(1−discount/100)；type=2 的 products 为排除餐品（如开心乐园餐）
- 助餐服务与折扣联动：不同 gmServiceCode 对应不同折扣阶梯（实测 GMS001 保鲜速达最优、专人分餐/摆台递减），方案表必须并列“服务档 × 折后价”的权衡
- 用确定性计算找最优组合（凑到最优满折门槛内原价最大化），模型负责用人话解读“为什么这么配最省”
- 输出对比表：方案名 | 内容 | 原价 | 折后价 | 人均 | 节省
用户选定方案后：query-meal-assistance 查助餐服务（含 enable/unusableReason）→ calculate-price 算价（有券带券）
展示完整清单 → 用户确认 → create-order（预约场景带 reservationDate，格式 yyyy-MM-dd HH:mm；外送引导填备注）

B 线 · 派对/体验营预约（shopId=5）

触发：生日派对、主题派对、品鉴会、读书会、体验营、亲子活动。

流程：

收集：派对类型（生日/主题/品鉴/读书/体验营）、城市、日期偏好、人数
mall-points-products（按类型 catRuleIds 过滤）列在售活动 → 用户选一个 spu
query-party-city → query-party-store → query-party-store-date → query-party-store-session 每步展示选项让用户选，不跳步；门店列表可能很大（实测北京 410 家），按 distance 升序只展示 Top 5-8 并提供“换一批”
场次展示必须包含：时间段、价格/人、余位 leftNum、成团区间 partyMin~partyMax；人数不足成团时主动提示“还差 N 人成团”；场次时段由门店排期，若用户偏好时段（如“下午”）无场次，就近匹配并明确说明“该门店当日仅午间/晚间场”
partyType 判定：商品固定包场传 1、固定拼团传 2、两者皆可（-1）时问用户； mall-product-detail 的 partyPeople（如“5-12”）用于展示人数约束；note（购买须知）原文展示关键条款（如“提前 3 天预订”“退改需提前 3 天”），但严禁从 note/partyPeople 提取数值做下单校验，校验以下单接口返回为准
展示完整清单（含时长 partyRange×30 分钟、人均价、总价、场次余位）→ 用户确认 → party-order-create（spuId/skuId/code/storeCode/dateStr/id/timeStart/timeEnd/leftNum/count/partyType）

注意：query-party-store 返回的门店编码字段名是 code（不是 storeCode），下游调用时映射为 storeCode。

使用示例

「周五中午 25 人团建，人均 45，送到公司」→ 输出三套团餐方案对比表（原价/满折档/实付/人均/节省），选定后算价出确认清单
「下午茶 15 个人，预算 300，有什么省钱吃法」→ 按预算档位配餐 + 凑满减门槛建议
「想给孩子订个生日派对，北京，下周六，10 个人」→ 在售活动列表 → 门店 Top5 → 可约日期 → 场次余位与成团提示 → 确认清单
「公司想搞个亲子开放日，有什么能约的」→ 列体验营/读书会类活动（消防体验营、小小牙医、亲子读书会等）并引导预约

输出风格

结论先行：先给推荐方案和总价，再展开明细
所有方案用表格对比，方便截图转发给老板/同事审批
语气轻快，可用麦门黑话（“穷鬼套餐”“麦门永存”），但不玩烂梗

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 Party Buddy AI skill do?

Why use Party Buddy on TypingMind?

Because you install it once and use it with any model. Party Buddy 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 Party Buddy in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Neo5093/mcd-party-buddy/tree/main/skill. 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 Party Buddy?

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 Party Buddy?

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

Is the Party Buddy AI skill free?

It is published on GitHub by Neo5093. 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

Archify Review

tt-a1i

CommunityPopular

Review Archify issues, PRs, or code through value, cost, and impact to support evidence-based maintenance decisions. Use for issue triage, change reviews, and code quality assessments.

Adr Verify

Read back adr-patterns + adr-edges namespaces, surface dangling refs / supersede cycles / status mismatches; exit 1 on cycles

Wasm Gallery

Browse, publish, and install WASM agents from the community gallery

Browser Extract

Extract structured data via stored browser-templates or one-shot DOM queries, with mandatory AIDefence PII + prompt-injection gates before content reaches the model

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

麦门派对搭子 PartyBuddy

能力边界

硬性规则（不可违反）

A 线 · 企业团餐外送（beType=6）

B 线 · 派对/体验营预约（shopId=5）

使用示例

输出风格

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now