← 返回 Skills 市场
med-critical-disease-review
作者
Unisound-LLM
· GitHub ↗
· v1.0.1
· MIT-0
90
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install med-critical-disease-review
功能描述
重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。
安全使用建议
Key things to check before installing or running this skill:
- Endpoint sanity: Confirm which endpoint will actually receive medical data — the SKILL.md mentions an internal IP (10.10.20.15:9010) but the code posts to https://shangbao.yunzhisheng.cn/.... Ask the maintainer which endpoint is intended and whether it is within your trusted network.
- Privacy promises vs. code behavior: The README claims PII will be stripped and nothing is persisted, but the visible code does not show any de-identification and it writes API responses and text summaries to ../runs by default. If you need to send PHI, require a proof of the redaction implementation or add a validation step yourself. Consider running with synthetic data first.
- Network/data exposure: This skill will transmit structured medical records to a remote service. If your organization restricts outbound network traffic for sensitive health data, run the skill in an isolated environment or block outbound access until you can verify the endpoint and its retention/processing policies.
- Local persistence: If you want to avoid files being written, run with explicit output paths (or inspect/run the code and remove/write-protection for save points). Search the full run.py for any other write operations (the provided run.py was truncated in the package listing).
- Testing and audit: Review the full run.py (the package listing is truncated) to confirm there are no hidden calls or additional endpoints. Test using non-sensitive sample records that simulate structure but contain no real patient identifiers.
Given these inconsistencies (endpoints, privacy claims vs code writes), treat the skill as suspicious until the author clarifies the redaction logic, the actual network destination, and data retention behavior.
功能分析
Type: OpenClaw Skill
Name: med-critical-disease-review
Version: 1.0.1
The skill bundle facilitates medical insurance claim assessments by processing various document formats and calling a remote API (shangbao.yunzhisheng.cn). It exhibits high-risk behaviors, including the execution of external system binaries (LibreOffice, Tesseract, pdftotext) via subprocess to parse user-supplied files and outbound network requests containing sensitive medical data. While these capabilities are plausibly necessary for the stated purpose, there is a notable discrepancy where the implementation in scripts/run.py lacks the PII de-identification logic explicitly claimed in the SKILL.md documentation, posing a data privacy risk.
能力评估
Purpose & Capability
The skill's stated purpose — calling an assessment service for 28 major-disease types — matches the code which builds a medicalRecord payload and posts it to an external assessment API (major_disease_assess.call_major_disease_assess). However SKILL.md also references an internal IP (http://10.10.20.15:9010) while the code's BASE_URL is https://shangbao.yunzhisheng.cn/..., which is an inconsistency you should confirm (different endpoints imply different network exposure).
Instruction Scope
The documentation claims strict desensitization and 'no local persistence', but the visible code does not implement any de-identification/PII redaction logic (validate_payload only checks structure) and the code writes the API response and natural-language output to disk by default (../runs/med-major-disease-assess/{disease}_resp.*). That contradicts the SKILL.md privacy promises and widens data exposure (sensitive medical data will be transmitted to a remote endpoint and may be saved locally unless you pass custom options).
Install Mechanism
This is an instruction+script skill with no install spec — no packages are force-installed. It optionally uses standard third-party Python packages (openpyxl, pypdf) and external binaries (libreoffice/soffice, pdftotext, tesseract) for input parsing. Those are expected for document processing and are documented as optional.
Credentials
The skill does not request environment variables or credentials (no secrets required), which is proportionate. However it will perform outbound HTTP(s) requests to shangbao.yunzhisheng.cn (and SKILL.md mentions an internal IP alternative). Because the payload contains medical records, network transmission to an external service is a privacy risk and should be validated against your data policies.
Persistence & Privilege
The skill is not marked always:true (no forced global enable), but despite SKILL.md claiming 'no local persistence', the code saves raw JSON and text outputs to disk by default and can create ../runs directories. That persistence behavior contradicts the documented guarantee and increases the attack surface for sensitive data on disk.
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-critical-disease-review - 安装完成后，直接呼叫该 Skill 的名称或使用
/med-critical-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`，支持直接处理多种主流文件格式（pdf/doc/docx/xls/xlsx/csv/txt/json）。
- SKILL.md 增加输入多格式自动归一化与统一运行入口说明。
- 更新依赖与外部工具说明，覆盖新格式支持（如 openpyxl、pypdf、LibreOffice、pdftotext、tesseract）。
- 兼容原有 `medicalRecord` JSON 入口，功能无迁移门槛。
v1.0.0
med-critical-disease-review 1.0.0
- Initial release.
- Provides intelligent major disease claim assessment for 28 disease types based on structured inpatient medical records.
- Outputs both original JSON results and natural language conclusions with supporting evidence.
- Enforces strict data privacy: de-identifies all sensitive information, processes data in-memory, and avoids local persistence.
- Includes minimal input validation before assessment.
- Command-line interface supports disease selection, input/output file specification, and timeout configuration.
元数据
常见问题
med-critical-disease-review 是什么？
重大疾病理赔智能评估（支持 28 种病种）。输入住院病历结构化数据，调用内网评估接口，输出原始 JSON 与自然语言结论（结论 + 证据）。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 90 次。
如何安装 med-critical-disease-review？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install med-critical-disease-review」即可一键安装，无需额外配置。
med-critical-disease-review 是免费的吗？
是的，med-critical-disease-review 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
med-critical-disease-review 支持哪些平台？
med-critical-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-critical-disease-review？
由 Unisound-LLM（@unisound-llm）开发并维护，当前版本 v1.0.1。
推荐 Skills