← 返回 Skills 市场
med-followup-record-struct
作者
Unisound-LLM
· GitHub ↗
· v1.0.1
· MIT-0
95
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install med-followup-record-struct
功能描述
将中文门诊复诊病历文本结构化为细粒度字段，输出 JSON（如现病史/既往史/诊断/处理意见等）。
安全使用建议
Key points before installing or using this skill:
- Do not run this on real patient data until the desensitization behavior is proven: the code sends the record text to a hardcoded remote API (shangbao.yunzhisheng.cn) with no de‑identification step or API key. This contradicts the SKILL.md privacy claims.
- The tool writes structured output to disk by default (../runs/med-followup-record-struct/structured.json) and can optionally save prepared text; expect local persistence unless you change the code or CLI options.
- If you need to use this for real PHI, request or implement one of the following: (a) a local/offline structuring backend, (b) an explicit, configurable endpoint plus required API key env var, (c) a vetted de‑identification/redaction step applied to the text before any network call (and verify it works on edge cases).
- If you cannot verify the remote service operator and the data minimization/de‑id guarantees, test only with synthetic or fully de‑identified samples.
- Suggested immediate changes to improve safety: remove or make API_URL configurable, require an API key or explicit opt‑in to enable network calls, implement and demonstrate de‑identification before sending, and document exactly what is persisted and where. If the author claims no persistence, ask them to fix code to avoid writing files by default or to make file saving opt‑in.
功能分析
Type: OpenClaw Skill
Name: med-followup-record-struct
Version: 1.0.1
The skill bundle is designed to structure Chinese medical records by extracting text from various file formats (PDF, DOCX, Excel, Images) and processing them via a disclosed external API (shangbao.yunzhisheng.cn). The implementation in `scripts/run.py` and `scripts/struct_followup_record.py` uses standard libraries and safe subprocess execution (non-shell) to call tools like LibreOffice and Tesseract. While it transmits medical data to a third-party service, this behavior is explicitly documented in `SKILL.md` along with privacy considerations, and no evidence of unauthorized data exfiltration, persistence, or malicious intent was found.
能力评估
Purpose & Capability
The skill purpose (structure Chinese outpatient follow‑up records) aligns with its code and the declared external API (record structuring). The hardcoded API endpoint (https://shangbao.yunzhisheng.cn/skills/record-struct/gen_abstract_by_his) is consistent with the stated capability, but embedding a remote service endpoint without configurable auth or opt‑out is a noteworthy design choice.
Instruction Scope
SKILL.md asserts strict de‑identification before sending data and claims no local persistence of inputs/intermediates. However, the implementation (scripts/struct_followup_record.py -> struct_followup_record -> call_followup_struct_api) reads the input file and sends the raw record_text directly to the remote API with no de‑identification step. The tool also writes the structured JSON to disk (default ../runs/...), and run.py offers a --save-prepared option to persist normalized text. These behaviors contradict the documented privacy claims.
Install Mechanism
No install spec or third‑party package installs are required by the skill itself; optional Python packages and external tools are documented (openpyxl, pypdf, soffice, pdftotext, tesseract) and are reasonable for file extraction tasks. Nothing is downloaded from an unknown URL by an installer.
Credentials
The skill requests no credentials or env vars, which reduces risk, but it unconditionally posts potentially sensitive text to a hardcoded third‑party endpoint without authentication or an explicit opt‑in/configurable backend. Lack of a configurable endpoint or a requirement to supply an API key means data may be sent to that remote server by default — this is disproportionate given the privacy-sensitive input.
Persistence & Privilege
The skill is not set to always:true and does not request elevated platform privileges. However, SKILL.md's claims of 'no local persistence' are false in practice: the code writes structured output to disk by default and can save normalized/prepared text. That mismatch between promise and behavior is a privacy/storage concern.
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-followup-record-struct - 安装完成后，直接呼叫该 Skill 的名称或使用
/med-followup-record-struct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 多种文件格式。
- 自动预处理并归一化输入，便于结构化复诊病历文本抽取。
- SKILL.md 文档详细补充了通用入口用法、依赖和参数说明。
- 保留原有纯文本入口，兼容旧有流程。
v1.0.0
med-followup-record-struct v1.0.0
- Initial release: Extracts and structures Chinese outpatient follow-up medical records into detailed JSON fields.
- Supports granular output for key sections such as current history, past history, diagnosis, and treatment suggestions.
- Ensures strict data privacy: personal identifiers are de-identified, no local storage, and secure encrypted transfer if using third-party services.
- Output format and usage instructions provided for easy integration.
- Clearly states medical and data boundaries: results are for structural extraction only, not medical advice.
元数据
常见问题
med-followup-record-struct 是什么？
将中文门诊复诊病历文本结构化为细粒度字段，输出 JSON（如现病史/既往史/诊断/处理意见等）。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 95 次。
如何安装 med-followup-record-struct？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install med-followup-record-struct」即可一键安装，无需额外配置。
med-followup-record-struct 是免费的吗？
是的，med-followup-record-struct 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
med-followup-record-struct 支持哪些平台？
med-followup-record-struct 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-followup-record-struct？
由 Unisound-LLM（@unisound-llm）开发并维护，当前版本 v1.0.1。
推荐 Skills