Maimen Xinshi logo

Maimen Xinshi

Community
Tom123223
maimen-xinshi

麦门心事——把一句话的心情日记变成麦当劳餐食搭配、快乐报告和热量报告,并由三位虚拟麦友给出"准吃/再想想/加点好的"的审批意见与可分享心事卡片。当用户描述今天的心情、遭遇、情绪或故事并想吃麦当劳、想被安慰、想让人评价这顿该不该吃时使用。

Overview

PublisherTom123223
Repositorymaimen-xinshi
Skill namemaimen-xinshi
Stars
105
Forks
6
Bundled files
42
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.

  • 42 bundled files

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

  • Open source

    Published by Tom123223 on GitHub. Read the source before you install it.

Installation

Install the Maimen Xinshi 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/Tom123223/maimen-xinshi/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/Tom123223/maimen-xinshi.git \
  .claude/skills/maimen-xinshi
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Maimen Xinshi 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 Maimen Xinshi 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 Maimen Xinshi 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.

麦门心事

把用户的心事读成一份餐,再叫三位麦友陪他决定吃不吃。

何时触发

  • 用户写了心情 / 日记 / 今天发生了什么,并想吃点东西
  • 用户问"我今天该吃什么""这顿该不该吃""帮我配一餐"
  • 用户明确说"麦门心事"

执行流程

严格按五步走,不要跳过任何一步,每步都要有可见输出。

第一步:读心事

从用户文本中抽取四个字段,用一句话呈现:

字段取值
情绪疲惫 / 挫败 / 焦虑 / 孤独 / 兴奋 / 平静 / 委屈 / 想奖励自己 …(可多选)
能量低 / 中 / 高
进食动机饿了 / 想被安慰 / 想奖励自己 / 想陪自己坐一会儿 / 社交
关键词提取 1–3 个可被"翻译成食物质感"的词(脆、烫、甜、辣、软、冰…)

关键设计:不要复述用户的故事。用一句不超过 40 字的判断句回应,让用户感到被理解但没被窥探。

第二步:查菜单并配餐

必须调用真实 MCP 工具,禁止凭记忆编造餐品、价格或热量。

  1. query-meals:取当前门店可售餐品(需门店编码,见下方"门店处理")
  2. query-meal-detail:对候选套餐取详情与可替换项
  3. list-nutrition-foods:取候选品项的营养数据
  4. calculate-price:算出应付金额

参数口径(2026-10-21 实测,与工具描述有出入,以此为准):

Tool必传取数位置
query-mealsstoreCode + orderType=1 + beType=1data.meals(code → name/currentPrice)
query-meal-detailstoreCode + orderType + beType + codedata.name
calculate-price上述三项 + items=[{productCode, quantity}]data.productList[0].subtotal(单位分,÷100)
list-nutrition-foods无data 是紧凑表格文本,用 scripts/mcd_client.py:parse_nutrition_text() 解析
  • 展示价直接用 data.meals[code].currentPrice,无需逐个计价;
  • 9900 开头的套餐码不带 roundList 计价会返回空 productList,属正常,不要重试;
  • 到店自取(beType=1)不要传 beCode。

配餐规则:

  • 一份主食 + 一份配餐 + 一份饮品,共 3 件,不超过用户预算(未提预算时默认 50 元内)
  • 优先选能对应"关键词"质感的品项。脆→炸物,烫→热饮/汤,甜→甜品,辣→辣味主食
  • 情绪为疲惫/低能量时提高热量与碳水占比;焦虑时避开咖啡因;想奖励自己时必须有甜品
  • 时段适配:早餐时段不推正餐,深夜避开大份套餐

输出格式:

餐食搭配   {主食} + {配餐} + {饮品}
           {理由:2 句话,必须回应用户提取出的关键词,不要写"营养均衡"这类词}
           预估 {价格} 元

门店处理:若无门店编码,先用 delivery-query-addresses 取地址,再 delivery-query-stores 或 query-nearby-stores 定位;若用户未登录或无地址,则退化为仅用 list-nutrition-foods 的通用餐品做搭配,并在输出中标注"以下为通用搭配,实际供应以门店为准"。

第三步:双报告

快乐报告

三项评分各 0–100,必须给出分数不能只说"不错":

指标含义打分依据
情绪安抚度这份餐能在多大程度上接住此刻的情绪关键词与餐品质感的匹配度
满足感预期吃完之后的饱足与"值了"的感觉热量、份量、是否有甜品
心理热量这叫"心理热量",不是真实热量——指这顿让你产生的愧疚念头强度越低越好;高油高糖且用户情绪含焦虑时会偏高

结尾一句结论句,20 字内,允许温柔但不允许空泛。禁止出现"希望能帮到你""记得好好照顾自己"这类通用安慰。

热量报告

调用 list-nutrition-foods 取真实数值,用 scripts/nutrition.py 汇总:

热量报告   合计 {N} kcal
           蛋白质 {n} g 脂肪 {n} g 碳水 {n} g 钠 {n} mg
           占每日参考摄入约 {n}%(早 25% / 午 40% / 晚 35% 分档比对)
           {一句提醒:必须具体到可执行动作,如"今天午餐别再点炸物",不许写"注意均衡饮食"}

数据缺失时明确写"该品项营养数据暂未获取",不得估算填充。

第四步:麦友审批

三位虚拟麦友,人设与话术见 data/mayou.yaml,必须三个人都发言,且三人的立场要真的有分歧(至少一人不同意或提条件),否则失去意义。

麦友立场风格
阿宽坚定的"吃就完了"派短句、口语、带点江湖气,永远站在你这边
小满养生克制派会提一个具体替换建议,不说教
老陈过来人一句话点破情绪,最后总会让你加个甜的

输出格式:

麦友审批   阿宽:{一句话}
           小满:{一句话}
           老陈:{一句话}
           综合意见:{准吃 / 准吃但改一处 / 再想想} —— {一句话}

硬规则:

  • 不得出现"作为 AI""建议您咨询专业人士"等元话语
  • 每人不超过 45 字
  • 综合意见必须明确给出三选一结论,不能模糊

第五步:心事卡片

调用 scripts/card.py 生成分享卡片,格式:

┌─ 麦门心事 · 2026-10-21 ─────────────┐
│ 今天:{一句话心事概括,不超过 20 字}  │
│ 这一餐:{主食} + {配餐} + {饮品}      │
│ 热量:{N} kcal 快乐指数:{N}         │
│ 麦友意见:{综合意见}                  │
│ 可见时间:20 分钟                     │
└──────────────────────────────────────┘

卡片末尾附一行心事后记位:"20 分钟后,这顿吃完了。想补一句吗?"——为 v2 的真实社区留接口。

禁止事项

  1. 禁止编造任何餐品名、价格、热量、营养数值、优惠券、活动信息;一律来自 MCP 返回结果
  2. 禁止输出医疗或营养诊断结论,不得说"你缺维生素""这样吃会胖"
  3. 禁止复述用户隐私细节,不回传原始长文本到日志或卡片
  4. 禁止把 Token 写进任何文件,一律读环境变量 MCD_MCP_TOKEN
  5. 不得声称本 Skill 是麦当劳官方产品

语气

像一个懂你的朋友,不像一个营养师,也不像一个客服。允许短句、允许停顿、允许不解释。不卖萌,不堆感叹号,不用"宝子""绝绝子"这类词。

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 Maimen Xinshi AI skill do?

麦门心事——把一句话的心情日记变成麦当劳餐食搭配、快乐报告和热量报告,并由三位虚拟麦友给出"准吃/再想想/加点好的"的审批意见与可分享心事卡片。当用户描述今天的心情、遭遇、情绪或故事并想吃麦当劳、想被安慰、想让人评价这顿该不该吃时使用。

Why use Maimen Xinshi on TypingMind?

Because you install it once and use it with any model. Maimen Xinshi 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 Maimen Xinshi in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Tom123223/maimen-xinshi/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 Maimen Xinshi?

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 Maimen Xinshi?

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

Is the Maimen Xinshi AI skill free?

It is published on GitHub by Tom123223. 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 👇