← Back to Skills Marketplace
unisound-llm

unisound-med-content-generation

by Unisound-LLM · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
112
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install unisound-med-content-generation
Description
医学科普、文档摘要、术语释义、教学案例与诊疗文书辅助生成。通过 --task 选择类型;仅含 `scripts/run.py`,可独立拷贝部署。
README (SKILL.md)

医学内容生成与解释

概述

面向医学内容生产与通俗化解释,输出须符合医学规范且标注为辅助材料。

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
explain 医学术语通俗释义
popular 医学科普内容生成
record-gen 诊疗文书辅助生成
summary 临床文档摘要生成
teach 临床教学案例生成

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 explain --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 explain --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 review could not verify the skill contents due to local sandbox file-read failure, so treat the result as inconclusive rather than a substantive approval.
Capability Assessment
Purpose & Capability
Unable to inspect metadata.json or artifact/ because the local command sandbox failed before file reads; no purpose mismatch can be concluded from the provided prompt alone.
Instruction Scope
Instruction scope could not be assessed from artifacts because file inspection was blocked by the runtime sandbox error.
Install Mechanism
Install behavior could not be reviewed because install specs and artifact contents were inaccessible.
Credentials
Environment access and proportionality could not be validated without reading the artifact files.
Persistence & Privilege
No artifact-backed persistence or privilege concern was available to evaluate; local inspection failed.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install unisound-med-content-generation
  3. After installation, invoke the skill by name or use /unisound-med-content-generation
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of medical content generation and explanation skill. - Supports multiple tasks: medical term explanation, popular science, clinical document drafting, summary generation, and teaching cases (switch via --task). - Flexible input methods: direct question, JSON/JSONL/text file, or stdin. - Outputs answers as structured JSON, suitable for integration and further processing. - Includes dry-run mode for input parsing without invoking the model. - Designed for secure deployment using internal medical LLM with API key authentication.
Metadata
Slug unisound-med-content-generation
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is unisound-med-content-generation?

医学科普、文档摘要、术语释义、教学案例与诊疗文书辅助生成。通过 --task 选择类型;仅含 `scripts/run.py`,可独立拷贝部署。 It is an AI Agent Skill for Claude Code / OpenClaw, with 112 downloads so far.

How do I install unisound-med-content-generation?

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

Is unisound-med-content-generation free?

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

Which platforms does unisound-med-content-generation support?

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

Who created unisound-med-content-generation?

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

💬 Comments