← Back to Skills Marketplace
unisound-llm

unisound-abnormal-indicator-alert

by Unisound-LLM · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
62
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install unisound-abnormal-indicator-alert
Description
病人端慢病管理异常指标预警。参考 Open Wearables 的 trends/anomalies reasoning 部分,构建慢病闭环能力。
README (SKILL.md)

异常指标预警

概述

本 skill 对应:病人端 / 慢病管理 / 异常指标预警。

要求:慢病闭环能力。

来源核验

  • 匹配来源:Open Wearables
  • 来源类型:公开开源健康数据平台
  • 来源链接:https://openwearables.io/
  • 匹配结论:部分匹配且可参考。Open Wearables 明确包含 health scoring、trends、anomalies、MCP 和可调阈值思路;本 skill 只借鉴异常识别结构,不照搬其可穿戴设备指标体系。

参考部分

只参考 Open Wearables 的 trends/anomalies reasoning 部分:

  • 指标阈值
  • 趋势识别
  • 异常识别
  • 风险提示
  • 可解释建议

不参考部分

  • 不参考可穿戴设备接入
  • 不参考睡眠、恢复、运动负荷等非慢病指标
  • 不参考完整平台部署
  • 不扩展为临床诊断系统

构建方式

OpenClaw 中应构建为一个独立的预警型 skill:

  • 输入血糖、血压、心率等慢病指标记录
  • 根据配置阈值判断是否异常
  • 输出异常等级、异常原因和建议动作
  • 对连续异常或明显超阈值记录给出复诊/随访提示

建议输入字段

  • indicator_type:指标类型,如血糖、血压、心率
  • value:指标值或指标对象
  • unit
  • measured_at
  • threshold_profile:阈值配置

建议输出字段

  • skill异常指标预警
  • indicator_type
  • is_abnormal
  • alert_level
  • reason
  • suggested_action

医疗边界

本 skill 只做基于规则的异常提示,不做诊断,不给出治疗方案。

快速开始

从本 skill 目录执行:

python3 scripts/run.py --input input.json --output output.json --appkey YOUR_KEY

最小输入示例

{
  "indicator_type": "blood_glucose",
  "value": 11.2,
  "unit": "mmol/L",
  "measured_at": "2026-04-29 08:00",
  "threshold_profile": {
    "high": 10.0
  },
  "suggested_action": "按既定随访规则提醒用户关注"
}

说明

本 skill 不内置医学阈值;所有阈值必须由调用方通过 threshold_profile 提供。

输出约定

输出 UTF-8 JSON,采用统一格式:

{
  "skill": "技能名称",
  "status": "ok",
  "data": { /* 结构化数据 */ },
  "text": "API 生成的 Markdown/自然语言内容,OpenClaw 直接渲染给用户"
}
  • data:本地预处理得到的结构化数据
  • text:内部医疗大模型生成的自然语言解读/分析/提醒,Markdown 格式

支持的输入格式

除 JSON 外,还支持以下格式(通过 --input-type 自动检测或手动指定):

格式 说明
JSON 默认,直接读取结构化输入
CSV / XLSX / XLS 表格数据,按列头自动映射字段
TXT / MD key:value 文本格式(支持中文/英文字段名)
PDF / DOC / DOCX 文档,提取文本后解析
PNG / JPG 等图片 OCR 提取文本后解析

文本格式示例

指标类型:blood_glucose
值:11.2
单位:mmol/L

CSV 格式示例

指标类型,值,单位
blood_glucose,11.2,mmol/L

统一入口附加参数

  • --input-type auto|pdf|doc|docx|xls|xlsx|csv|txt|json:输入类型;默认 auto
  • --sheet STRING:读取 Excel 时指定 sheet(可选)。
  • --encoding STRINGtxt/csv 编码(默认:utf-8)。
  • --save-prepared:保存预处理后的 JSON,便于调试。
  • --appkey STRING必填。调用内部医疗大模型的鉴权 key,由平台分配。

依赖

运行环境

  • Python 3.7+

Python 第三方包(可选,按输入格式需要)

包名 用途 必要条件
openpyxl 读取 .xlsx 文件 输入为 xlsx 时必须
pypdf 提取 PDF 文本 输入为 pdf 时必须

外部工具(可选,按输入格式需要)

工具 用途 必要条件
LibreOffice (soffice) 转换 .doc / .xls 输入为 doc/xls 时必须
pdftotext(poppler-utils) 提取 PDF 文本 输入为 pdf 且未安装 pypdf 时
tesseract(含 chi_sim+eng) 图片 OCR 输入为图片时必须

仅使用 JSON 输入时,无需安装任何第三方包或外部工具。

模型配置

本 skill 执行时通过内部医疗大模型进行推理:

  • endpoint:https://maas-api.hivoice.cn/v1/chat/completions
  • model:u1-insuremed
  • 协议:OpenAI Chat Completions(兼容标准 /v1/chat/completions)
  • 鉴权:通过 --appkey 参数传入 Bearer token,由用户在 OpenClaw 中调用时提供

本 skill 强制走 API 推理,无本地透传模式。

Usage Guidance
Do not treat this as a complete approval review. Rerun the scan when metadata.json and the artifact directory can be inspected, then decide based on the actual skill contents.
Capability Analysis
Type: OpenClaw Skill Name: unisound-abnormal-indicator-alert Version: 1.0.0 The skill is a medical indicator analysis tool that processes health data (e.g., blood glucose, blood pressure) from various file formats and uses a Unisound LLM API (hivoice.cn) for interpretation. The code in `scripts/preprocess.py` and `scripts/run.py` uses standard practices for document parsing (LibreOffice, Tesseract, pypdf) and API communication, with no evidence of malicious intent, data exfiltration, or harmful prompt injection.
Capability Tags
requires-oauth-tokenrequires-sensitive-credentials
Capability Assessment
Purpose & Capability
No artifact-backed assessment could be completed because the requested metadata.json and artifact directory were not readable through the available workspace command runner.
Instruction Scope
Instruction scope could not be evaluated from artifact text in this run.
Install Mechanism
Install behavior could not be evaluated from artifact text in this run.
Credentials
Environment access and proportionality could not be evaluated from artifact text in this run.
Persistence & Privilege
Persistence and privilege behavior could not be evaluated from artifact text in this run.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install unisound-abnormal-indicator-alert
  3. After installation, invoke the skill by name or use /unisound-abnormal-indicator-alert
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the skill, renamed to **med-patient-abnormal-indicator-alert**. - Provides patient-side abnormal indicator alerting for chronic disease management, referencing Open Wearables' trends/anomalies reasoning. - Supports structured input (e.g., blood glucose, blood pressure, heart rate) with customizable threshold profiles. - Outputs include abnormality level, reason, and suggested actions, with explanations in Markdown. - Accepts multiple input formats: JSON, CSV/XLS, TXT/MD, PDF/DOC, and image (OCR). - Requires external API and appkey for medical model reasoning; no default thresholds are built-in.
Metadata
Slug unisound-abnormal-indicator-alert
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is unisound-abnormal-indicator-alert?

病人端慢病管理异常指标预警。参考 Open Wearables 的 trends/anomalies reasoning 部分,构建慢病闭环能力。 It is an AI Agent Skill for Claude Code / OpenClaw, with 62 downloads so far.

How do I install unisound-abnormal-indicator-alert?

Run "/install unisound-abnormal-indicator-alert" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is unisound-abnormal-indicator-alert free?

Yes, unisound-abnormal-indicator-alert is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does unisound-abnormal-indicator-alert support?

unisound-abnormal-indicator-alert is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created unisound-abnormal-indicator-alert?

It is built and maintained by Unisound-LLM (@unisound-llm); the current version is v1.0.0.

💬 Comments