← Back to Skills Marketplace
unisound-llm

unisound-med-rx-safety-ethics

by Unisound-LLM · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
44
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install unisound-med-rx-safety-ethics
Description
处方审核(问答/单选/多选题型)、医疗安全规范与医学伦理法规问答;仅含 `scripts/run.py`,可独立拷贝部署。
README (SKILL.md)

处方审核与安全伦理

概述

处方合理性与医疗安全、伦理合规类问题,严格按题目要求的作答格式输出。

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
ethics 医学伦理与法规问答
rx-msq 处方审核(多选题题型)
rx-scq 处方审核(单选题题型)
rx-sq 处方审核(问答题型)
safety 医疗安全制度与规范问答

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 ethics --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 ethics --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
This result is inconclusive: installation decisions should wait for a successful review of metadata.json and the artifact directory.
Capability Assessment
Purpose & Capability
Not assessed from artifact content because local workspace commands failed before metadata.json or artifact files could be read.
Instruction Scope
Not assessed from artifact content because local workspace commands failed before SKILL.md or related files could be read.
Install Mechanism
Not assessed from artifact content because install artifacts could not be read.
Credentials
Not assessed from artifact content because capability and manifest files could not be read.
Persistence & Privilege
Not assessed from artifact content because no persistence or privilege evidence could be inspected.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install unisound-med-rx-safety-ethics
  3. After installation, invoke the skill by name or use /unisound-med-rx-safety-ethics
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of med-llm-rx-safety-ethics - Provides prescription review Q&A (multiple choice, single choice, free-form), medical safety procedures, and medical ethics/legal Q&A. - Callable via command-line with flexible input methods: direct question, file input, or stdin. - Supports task switching for various scenarios (ethics, rx-msq, rx-scq, rx-sq, safety) using --task or input metadata. - Outputs structured, parseable JSON with detailed fields (status, question, answer, etc.). - Requires internal medical LLM and appkey for authentication. - Fully self-contained; can be directly copied and deployed.
Metadata
Slug unisound-med-rx-safety-ethics
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is unisound-med-rx-safety-ethics?

处方审核(问答/单选/多选题型)、医疗安全规范与医学伦理法规问答;仅含 `scripts/run.py`,可独立拷贝部署。 It is an AI Agent Skill for Claude Code / OpenClaw, with 44 downloads so far.

How do I install unisound-med-rx-safety-ethics?

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

Is unisound-med-rx-safety-ethics free?

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

Which platforms does unisound-med-rx-safety-ethics support?

unisound-med-rx-safety-ethics is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created unisound-med-rx-safety-ethics?

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

💬 Comments