← Back to Skills Marketplace
unisound-llm

unisound-med-term

by Unisound-LLM · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
45
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install unisound-med-term
Description
医学名词规范解释。由调用方提供题目文本或含 `question` 字段的结构化输入,经内部医疗大模型按题干约束生成作答;仅含 `scripts/run.py`,可独立拷贝部署。
README (SKILL.md)

医学名词规范解释

概述

对给定医学名词给出准确、精炼的定义与临床语境提示。

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 -

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

# 命令行直接给题
python3 scripts/run.py --question "题干……" --appkey YOUR_KEY

# 从任意路径的 jsonl 取一条(与文件名无关)
python3 scripts/run.py --input /path/to/items.jsonl --index 0 --appkey YOUR_KEY

参数

  • --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 statusquestionanswerrecord_indexmetamodelinput_modeinput_path(来自文件时非空)等;skill 为本任务标题。

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
Install only if you trust the publisher and the hivoice.cn model endpoint. Do not include identifiable patient data unless your organization allows it, keep the app key private, and avoid overriding --api-url unless the destination is trusted.
Capability Analysis
Type: OpenClaw Skill Name: unisound-med-term Version: 1.0.0 The skill is a legitimate utility for medical term explanation using the Unisound medical LLM API. The script (scripts/run.py) implements a standard CLI interface for processing local files or stdin and communicating with a specific endpoint (maas-api.hivoice.cn). No indicators of data exfiltration, malicious execution, or prompt injection were found.
Capability Assessment
Purpose & Capability
The documented purpose matches the code: it parses a user-supplied question and calls a disclosed medical LLM endpoint. Medical inputs and outputs should still be treated as sensitive and advisory.
Instruction Scope
The instructions define explicit input modes, a dry-run mode, and optional output behavior. No hidden prompt override, forced tool use, or autonomous background behavior is shown.
Install Mechanism
There is no install script or package download, but the bundled _meta.json identifiers differ from the registry-facing name/owner, so users should verify provenance.
Credentials
The skill reads only caller-selected input or stdin and can write a caller-selected output file, but live use transmits the question text to the configured external model API.
Persistence & Privilege
No persistence, background worker, privilege escalation, or credential storage is shown. The API key is used for the live model call and is not written by the visible code.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install unisound-med-term
  3. After installation, invoke the skill by name or use /unisound-med-term
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of med-eval-med-term skill. - Provides accurate, concise definitions and clinical context for medical terms. - Flexible input: accepts questions directly, from file (.json, .jsonl, or plain text), or stdin. - Model and API endpoint are configurable; default is u1-insuremed. - Outputs structured JSON with model response and metadata. - Includes command-line examples and detailed parameter descriptions.
Metadata
Slug unisound-med-term
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is unisound-med-term?

医学名词规范解释。由调用方提供题目文本或含 `question` 字段的结构化输入,经内部医疗大模型按题干约束生成作答;仅含 `scripts/run.py`,可独立拷贝部署。 It is an AI Agent Skill for Claude Code / OpenClaw, with 45 downloads so far.

How do I install unisound-med-term?

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

Is unisound-med-term free?

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

Which platforms does unisound-med-term support?

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

Who created unisound-med-term?

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

💬 Comments