← Back to Skills Marketplace
unisound-llm

unisound-med-clinical-decision

by Unisound-LLM · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
106
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install unisound-med-clinical-decision
Description
专病诊疗、基层处置、全科辅助、结局分析、病情分析与慢病管理。通过 --task 选择场景;仅含 `scripts/run.py`,可独立拷贝部署。
README (SKILL.md)

临床决策与健康管理

概述

面向临床决策与健康管理类问题,给出结构化建议并强调需结合实际情况。

具体场景通过 --task 切换系统提示词(见下表),能力依赖内部医疗大模型;集成方也可通过 --system-prompt 完全自定义。

--task 能力
analysis 病情分析与量表计算问答
care 基层诊疗处置建议
outcome 治疗效果与结局分析
phm 慢病个性化健康管理
primary 基层全科诊疗辅助
treat 专病诊疗方案制定

本能力与具体业务请求解耦:平台或调用方如何组织用户输入由集成方决定;此处只约定如何把题目交给脚本(见下)。

题目输入(三选一)

  1. --question:直接传入完整题干字符串。
  2. --input PATH
    • .jsonl:每行一个 JSON 对象,须含非空字符串字段 question;可用 --index / --batch / --match-id 选取记录;
    • .json:单个对象,须含 question
    • 其他扩展名:按 UTF-8 纯文本整文件作为题干。
    • - 时从 stdin 读取一条 JSON(含 question)或纯文本。
  3. stdin(且未传 --question / --input、且 stdin 非 TTY):读入 JSON 对象或纯文本,规则同 -

可在 JSON 的 other.task 中指定任务类型(与 --task 等价;命令行 --task 优先)。

模型

  • 默认 u1-insuremed,接口 https://maas-api.hivoice.cn/v1/chat/completions(可通过参数覆盖)。

用法示例

# 指定任务类型与题干
python3 scripts/run.py --task analysis --question "题干……" --appkey YOUR_KEY

# 从 jsonl 取题(other.task 可省略若命令行已传 --task)
python3 scripts/run.py --task analysis --input /path/to/items.jsonl --index 0 --appkey YOUR_KEY

参数

  • --task必填(除非 other.task 已给出)。见上表。
  • --question / --input:见上,与 stdin 三选一(--question--input 不可同时使用)。
  • --appkey STRING必填--dry-run 时除外)。内部医疗大模型鉴权 key。
  • --index--match-id--batch:仅对 .jsonl 生效。
  • --dry-run:不调用模型,仅输出解析后的题目 JSON。
  • --model--api-url--temperature--timeout--system-prompt:调模型参数。
  • --output PATH:另存完整 JSON(批量为 NDJSON)。
  • --text-only:标准输出仅打印模型答案文本。

输出

默认可解析 JSON:含 statustasktask_titlequestionanswerrecord_indexmetamodelinput_modeinput_path 等;skill 为本 skill 标题。

合规说明

输出为模型辅助信息,不构成正式诊疗决策;涉及真实患者数据须先脱敏并遵守院内流程。

Usage Guidance
Do not rely on this review as an approval. Re-run the scan in an environment where metadata.json and artifact/ can be read, then evaluate the actual artifact evidence.
Capability Assessment
Purpose & Capability
Workspace file inspection failed before metadata or artifact contents could be read, so purpose-to-capability coherence could not be verified.
Instruction Scope
SKILL.md and any runtime instructions were not accessible through the execution sandbox, so instruction scope could not be assessed.
Install Mechanism
Install specs and file manifest could not be read, so provenance and setup behavior could not be validated.
Credentials
Environment access could not be compared against the stated purpose because artifact contents were unavailable.
Persistence & Privilege
Persistence, privilege, and credential behavior could not be checked from the supplied files.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install unisound-med-clinical-decision
  3. After installation, invoke the skill by name or use /unisound-med-clinical-decision
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the med-llm-clinical-decision skill for clinical decision support and health management. - Supports multiple scenarios including specialty diagnosis, primary care, general practice assistance, outcome analysis, condition review, and chronic disease management via the --task parameter. - Uses a command-line interface with flexible input options: direct questions, JSON/JSONL files, or stdin. - Integrates with the internal medical LLM (default: u1-insuremed); supports overriding model/api settings. - Outputs structured JSON results with detailed task, input, and model information. - Emphasizes compliance: model output is for clinical assistance and not formal diagnosis; requires data de-identification.
Metadata
Slug unisound-med-clinical-decision
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is unisound-med-clinical-decision?

专病诊疗、基层处置、全科辅助、结局分析、病情分析与慢病管理。通过 --task 选择场景;仅含 `scripts/run.py`,可独立拷贝部署。 It is an AI Agent Skill for Claude Code / OpenClaw, with 106 downloads so far.

How do I install unisound-med-clinical-decision?

Run "/install unisound-med-clinical-decision" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is unisound-med-clinical-decision free?

Yes, unisound-med-clinical-decision is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does unisound-med-clinical-decision support?

unisound-med-clinical-decision is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created unisound-med-clinical-decision?

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

💬 Comments