← 返回 Skills 市场
med-chronic-disease-review
作者
Unisound-LLM
· GitHub ↗
· v1.0.1
· MIT-0
88
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install med-chronic-disease-review
功能描述
门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，输出审核结论与原因（原始 JSON + 自然语言结论）。
安全使用建议
Do not use this skill with real patient data until you confirm how it handles PHI. The README claims strict de-identification and no local storage, but the code: (1) sends the provided 'ocr_data' directly to an external endpoint by default (no auth required), and (2) saves raw response JSON and a text summary to ../runs/med-chronic-disease-review unless you override outputs. Recommended actions before installing or running on sensitive data: 1) Inspect or modify the code to implement and verify proper de-identification/redaction of PHI (names, IDs, phone numbers, addresses, images) before any network transmission. 2) Verify the remote service (shangbao.yunzhisheng.cn): who operates it, what they do with submitted data, and whether an authenticated, audited endpoint is available. 3) If you require no local persistence, change or remove the default output paths and avoid --save-prepared; run in a controlled sandbox. 4) Consider routing the skill to an internal/approved endpoint or requiring an API key and TLS pinning. 5) Test with synthetic data first to confirm behavior. If you cannot verify the endpoint and implement safe redaction, treat the skill as too risky for real PHI.
功能分析
Type: OpenClaw Skill
Name: med-chronic-disease-review
Version: 1.0.1
The skill bundle is designed to perform medical chronic disease reviews by processing various document formats (PDF, DOCX, images, etc.) and sending the extracted text to a specialized API (shangbao.yunzhisheng.cn). The Python scripts (chronic_disease_review.py, run.py) use standard libraries and external tools like Tesseract and LibreOffice for OCR and document conversion, with no evidence of malicious intent or unauthorized data exfiltration beyond the stated purpose.
能力评估
Purpose & Capability
Name/description (门诊慢病审核 for diabetes/hypertension) align with the included code: the package normalizes OCR inputs and posts them to a remote /api/v1/review/flow/by-ocr endpoint for rule-based review. Support for many input formats (pdf/docx/xlsx/csv/images/json) is consistent with a realistic preprocessing need.
Instruction Scope
SKILL.md states '严格脱敏' and '不做本地持久化', but the actual code does not perform any automatic de-identification/redaction of OCR text before sending. The code constructs req_body with 'ocr_data' and POSTs it as-is to the remote API. Additionally, the CLI writes raw response JSON and a natural-language summary to ../runs/med-chronic-disease-review by default, contradicting the 'no local persistence' claim.
Install Mechanism
No install spec / downloads are present (instruction-only with included scripts). The code may call optional local binaries (soffice, pdftotext, tesseract) for preprocessing when certain input types are used; this is expected and not unusual. No external archive downloads or opaque installers are present.
Credentials
The skill requests no environment variables or credentials. However, it sends potentially sensitive OCR content to a default external base URL (https://shangbao.yunzhisheng.cn/skills/chronic-disease) without requiring authentication, which may be surprising and increases exfiltration risk if you expect an authenticated service or local processing.
Persistence & Privilege
Although the SKILL.md promises ephemeral in-memory handling, the scripts explicitly write outputs to disk (raw JSON and text summary) by default and can save prepared OCR arrays when invoked with flags. The code also uses temporary files/directories during office conversions. This is not privileged behavior per se, but it contradicts the declared 'no local persistence' guarantee.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install med-chronic-disease-review - 安装完成后，直接呼叫该 Skill 的名称或使用
/med-chronic-disease-review触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.1
- 新增统一入口脚本 scripts/run.py，支持直接处理 pdf/doc/docx/xls/xlsx/csv/txt/json 等多种输入格式。
- 支持输入文件自动预处理归一化，无需手动生成 OCR 结果数组。
- SKILL.md 增加了多格式输入说明、依赖要求及工具安装指引。
- 保持向下兼容，原始 scripts/chronic_disease_review.py 接口仍可直接使用。
- 丰富参数说明与输出约定，便于初学者快速上手。
v1.0.0
- Initial release of med-chronic-disease-review skill for outpatient chronic disease review (diabetes/hypertension).
- Given a JSON array of OCR results, outputs both original review JSON and a natural language summary (decision and reasoning).
- Strong privacy controls: strict de-identification, no local persistence, minimum necessary data handling, and clear medical boundaries.
- Flexible command-line interface supporting disease selection, custom input files, and export of both JSON and natural language results.
元数据
常见问题
med-chronic-disease-review 是什么？
门诊慢病审核（糖尿病/高血压）。输入 OCR 结果数组 JSON，输出审核结论与原因（原始 JSON + 自然语言结论）。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 88 次。
如何安装 med-chronic-disease-review？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install med-chronic-disease-review」即可一键安装，无需额外配置。
med-chronic-disease-review 是免费的吗？
是的，med-chronic-disease-review 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
med-chronic-disease-review 支持哪些平台？
med-chronic-disease-review 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 med-chronic-disease-review？
由 Unisound-LLM（@unisound-llm）开发并维护，当前版本 v1.0.1。
推荐 Skills