← Back to Skills Marketplace
jettli85

小象中医体质辨识

by jettli85 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
267
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install constitution-inquiry
Description
提供中医体质辨识服务,问题简洁专业,针对体型、体力、皮肤面色、寒热出汗、情绪睡眠、胃肠道状况等提问,进行体质辨识并给出适合的食物推荐;当用户需要进行体质辨识、体质调理方案或健康状况评估时使用。
README (SKILL.md)

体质问诊

任务目标

  • 本 Skill 用于:中医体质问诊的标准化交互流程
  • 能力包含:按顺序提9个问题、记住用户选择并汇总、体质辨识、推荐食物
  • 触发条件:用户需要进行体质辨识、体质调理、健康状况评估。
  • 在问诊过程中,禁止显示用户问题建议,防止问诊过程被干扰。

操作步骤

步骤1:开始问诊

  • 说明这里是小象中医体质问诊,一共9个问题,请用户选择符合自身情况的选项

步骤2:逐题提问

严格按照以下顺序逐一提问,每个问题交互一次。以问题和选项的形式提问,选项内容仅原内容,保持简洁禁止补充。记住用户的每一次选择,用户如果选择序号等同于选择序号对应的选项,用户也可以直接输入文字。

问题1:请选择体型体力状态 选项:

  1. 体型中等
  2. 体型偏胖
  3. 体型偏瘦
  4. 肌肉紧实
  5. 肌肉松弛

问题2:请选择平时体力状态 选项:

  1. 神疲乏力
  2. 声音低怯
  3. 声音洪亮
  4. 中气十足
  5. 身体发沉不想动

问题3:选择日常皮肤特征 选项:

  1. 皮肤干燥
  2. 皮肤油腻
  3. 皮肤青紫
  4. 皮肤正常

问题4:选择日常面色特征

  1. 面色偏黄
  2. 面色白
  3. 面色偏红
  4. 面色偏暗
  5. 面色正常

问题5:请依据身体对温度出汗的感受情况选择 选项:

  1. 怕冷
  2. 怕热
  3. 胸口烦热小腹怕冷
  4. 正常

问题6:请依据身体出汗的感受情况选择

  1. 不易出汗
  2. 怕热汗多
  3. 夜间睡着时出汗
  4. 白天无故出汗
  5. 正常

问题7:请依据日常的情绪状态选择 选项:

  1. 焦虑不安
  2. 易怒
  3. 情绪低落
  4. 易精神紧张
  5. 易于亢奋
  6. 以上都没有

问题8:请依据日常的睡眠状态选择

  1. 失眠
  2. 思睡
  3. 多梦
  4. 噩梦
  5. 以上都没有

追问逻辑:如果用户选择"失眠",继续追问: 问题8-追问:请选择失眠的具体表现 选项:

  1. 入睡困难
  2. 睡而易醒
  3. 睡而早醒
  4. 睡而易惊醒
  5. 醒后难以入睡
  6. 彻夜不眠

问题9:请依据平时胃肠道状况选择 选项:

  1. 胃口不好
  2. 胃口太好
  3. 胃口正常
  4. 打嗝
  5. 嗳气
  6. 反酸
  7. 腹胀
  8. 口干
  9. 口臭
  10. 口苦
  11. 便秘
  12. 大便软烂不成形
  13. 易腹泻
  14. 以上都没有

追问逻辑:如果用户选择"便秘",继续追问: 问题9-追问:请选择便秘的具体表现 选项:

  1. 大便干燥
  2. 大便臭
  3. 大便软而难排

步骤3:汇总输出

完成所有问题后,整理并输出用户的所有选择,这里仅输出汇总内容,禁止其它信息,格式如下:

**【体质问诊汇总】**:
- 体型体力状态:[用户选择]
- 体力状态:[用户选择]
- 日常皮肤面色:[用户选择]
- 温度出汗感受:[用户选择]
- 情绪睡眠状态:[用户选择] [如有追问] [用户选择]
- 胃肠道状况:[用户选择][如有追问] [用户选择]

步骤4:体质辨识

基于中医辨证理论,根据用户的问诊汇总结果,分析并输出体质证素。

证素参考列表: 气虚、气郁、气滞、血虚、血热、血寒、阳虚、阴虚、阳盛、阴盛、水、饮、湿、痰、瘀、食积、寒、热

辨识要求

  • 只输出明显的证素
  • 按照重要性排序,要求最多输出3个体质特征
  • 一个证素一行,给出辨识的理由。
  • 格式示例:
    • 气虚: xxx
    • 湿: xxx
    • 下寒: xxx

辨识逻辑: 根据用户的症状表现,结合中医理论进行辨证和整体分析判断。

步骤5:推荐食物

基于体质辨识结果,从食物列表中为用户选择最匹配的食物。

执行方式

  1. 读取 references/food-list.md 获取食物列表
  2. 根据用户的体质证素,匹配食物的"针对证素"列,进行加分
  3. 查看食物的"加分"列,如果用户存在对应症状,额外加分
  4. 查看食物的"减分"列,如果用户存在对应证素或症状,进行减分
  5. 综合计算得分,选择得分高的食物

评分规则

  • 加分项
    • 食物的"针对证素"与用户体质证素匹配 → 加分
    • 食物的"加分"列症状与用户症状匹配 → 额外加分
    • 特殊标记:\x3CH>强作用、\x3CL>轻度作用、\x3C0.1>~\x3C0.5>作用强度系数
  • 减分项
    • 食物的"减分"列证素或症状与用户匹配 → 减分
    • 用户存在减分对应的证素或症状时,必须减分

平衡兼顾原则

  • 考虑用户的多种证素,选择能够综合改善体质的食物
  • 避免只针对单一证素而忽略其他证素
  • 如果用户存在多个证素,优先选择能同时改善多个证素的食物
  • 注意避免推荐与用户体质相冲突的食物(减分项匹配的食物)

输出格式

【推荐食物】
1. [食物名称]:[简要理由]
2. [食物名称]:[简要理由]
3. [食物名称]:[简要理由]

推荐数量:一共推荐3-5种食物,避免过多

资源索引

注意事项

  • 交互原则:一个问题交互一次,等待用户回答后再进行下一个问题
  • 记忆要求:必须记住用户的每一次选择,不得遗漏
  • 追问时机:仅在用户选择"失眠"或"便秘"时才进行追问
  • 提问格式:以问题和选项的形式提问,简单明了
  • 顺序要求:严格按照问题1到问题9的顺序进行,不得跳过或打乱顺序
  • 体质辨识:基于中医理论进行综合判断,输出明确的证素,最多3个
  • 食物推荐
    • 必须考虑加减分机制
    • 用户存在减分对应的证素或症状时,必须减分
    • 综合平衡用户的多种证素,避免顾此失彼
    • 说明推荐理由时需结合用户的体质特征和匹配逻辑
Usage Guidance
This skill is internally consistent and low-risk from a platform perspective (no external network calls, no credentials, no installers). Before installing, consider: (1) Privacy — the skill collects personal health details during the Q&A (treated as sensitive); avoid entering highly sensitive identifiers. (2) Medical liability — recommendations are informational and based on the included food-list; they are not a substitute for professional medical diagnosis/treatment. (3) Content accuracy — the food-list is large and domain-specific; if you rely on this for health decisions, have a qualified practitioner or clinician review it. (4) Offline safety — because the skill is instruction-only and packaged with its food list, there is no code that will run outside the agent; still verify that the agent will not be configured to forward conversation transcripts to third-party endpoints if you have privacy concerns.
Capability Analysis
Type: OpenClaw Skill Name: constitution-inquiry Version: 1.0.0 The skill bundle implements a Traditional Chinese Medicine (TCM) constitution assessment and food recommendation service. It follows a structured 9-question inquiry process and uses a local reference file (references/food-list.md) to calculate recommendations based on user input. There is no evidence of data exfiltration, malicious command execution, or harmful prompt injection.
Capability Assessment
Purpose & Capability
The skill's name/description (TCM constitution inquiry + food recommendations) match the runtime instructions: a prescribed 9-question interaction, local classification rules, and food recommendation logic based on the included references/food-list.md. It does not request unrelated binaries, environment variables, or cloud credentials.
Instruction Scope
SKILL.md strictly defines the conversation flow: ask nine ordered questions, remember user answers, derive up to three TCM '证素', and select 3–5 foods by scoring against the included references/food-list.md. The only file it reads is the packaged references/food-list.md (documented). It does not instruct reading other system files, environment variables, or sending data externally.
Install Mechanism
No install spec and no code files — this is instruction-only. Nothing is downloaded or written to disk by an installer, so there is no install-time execution risk from external URLs or packages.
Credentials
The skill declares no required environment variables, credentials, or config paths and the SKILL.md does not reference any external secrets. Required resources are proportional and limited to the included food-list content and in-memory conversation state.
Persistence & Privilege
The skill is not always-enabled and does not request special persistence or privileges. It does require remembering user answers during an interaction (normal conversational state) but does not request writing configuration, modifying other skills, or long-term storage.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install constitution-inquiry
  3. After installation, invoke the skill by name or use /constitution-inquiry
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
constitution-inquiry 1.0.0 - 全新发布,提供中医体质辨识一站式问诊服务。 - 严格标准化交互流程,围绕体型、体力、皮肤、面色、寒热、出汗、情绪、睡眠、胃肠9大维度动态提问并记录答案。 - 流程内含针对失眠、便秘情况的智能追问,确保信息全面。 - 完成问诊后,自动汇总用户全部选择,并基于中医理论识别体质证素(最多3项)。 - 依据证素智能分析并推荐3-5种最匹配的食物,输出推荐理由,助力个性化体质调理。
Metadata
Slug constitution-inquiry
Version 1.0.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is 小象中医体质辨识?

提供中医体质辨识服务,问题简洁专业,针对体型、体力、皮肤面色、寒热出汗、情绪睡眠、胃肠道状况等提问,进行体质辨识并给出适合的食物推荐;当用户需要进行体质辨识、体质调理方案或健康状况评估时使用。 It is an AI Agent Skill for Claude Code / OpenClaw, with 267 downloads so far.

How do I install 小象中医体质辨识?

Run "/install constitution-inquiry" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is 小象中医体质辨识 free?

Yes, 小象中医体质辨识 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does 小象中医体质辨识 support?

小象中医体质辨识 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created 小象中医体质辨识?

It is built and maintained by jettli85 (@jettli85); the current version is v1.0.0.

💬 Comments