M

Medical Device Non-clinical Research Checker

作者:注册老炮@MedXpert I SynomosAIv3

医疗器械非临床研究判定器——基于官方规则源的零依赖决策支持工具,JSON IR 输出,覆盖 TH-MED-001 域(医疗器械全链路)。

下载量
332
点赞
83
价格
¥0.10

技能文档

---
name: non-clinical-checker
title: "Medical Device Non-clinical Research Checker"
slug: non-clinical-checker
display_name: 医疗器械非临床研究判定器
display_name_en: Medical Device Non-clinical Research Checker
version: 1.0.1
category: medtech-reg
author: SynomosAI
license: MIT
allowed-tools: Read, Glob, Grep, Bash, Write, WebFetch
description: 医疗器械非临床研究判定器——基于官方规则源的零依赖决策支持工具,JSON IR 输出,覆盖 TH-MED-001 域(医疗器械全链路)。
description_zh: "医疗器械非临床研究判定器——基于官方规则源的零依赖决策支持工具,JSON IR 输出,覆盖 TH-MED-001 域(医疗器械全链路)。"
description_en: "Medical device non-clinical research determination tool: zero-dependency decision support with JSON IR output (domain TH-MED-001, full device chain)."
tags: [医疗器械, 合规, 判定器, TH-MED-001, non-clinical-checker, medtech-reg]
classification:
  skillhub: ["medtech-reg", "medical-device", "compliance"]
  clawhub: ["productivity", "development", "search"]
  iso_25010: ["Functional suitability"]
read_when:
  - 研发立项初期依据 TH-MED-001 域规则判定研究阶段是否属非临床范畴
  - 临床/注册申报前验证已产生非临床数据的合规性与有效性
  - 审查内部设计方案是否存在违反官方规则的非临床实验安排
risk_tier: medium
risk_rationale: "调用 API/读写文件/本地执行,最小权限,密钥走 Secret;若实际涉对外代执行(push/发布/发送/上架)须人工复评,改 high 并走负责人批准。"
platforms: [windows, macos, linux]
platform_compatibility: [windows, macos, linux]
ai_protocol: true
spec: usk/1.0
interface:
  type: prompt
  entry_point: SKILL.md
  runtime: none
  call_pattern: prompt
output_schema:
  stdout: structured JSON IR
  exit_code: rc=0 ok / rc=1 warning / rc=2 bad input
changelog: "1.0.1: Bilingual rewrite (EN-first) + read_when; risk_rationale ref neutralized; 1.0.0 initial"
---

> 凡自治之物 · LGD 治理学 · 创造术家族 | 评测协议:skill-quality-gate

## English

# Medical Device Non-clinical Research Checker

## When to use
1. At R&D project initiation, use TH-MED-001 domain rules to quickly determine whether a research stage falls under non-clinical research.
2. Before clinical trial or registration submission, verify the compliance and validity of non-clinical data already produced.
3. When an R&D organization needs to review internal design plans for non-clinical arrangements that violate official rules.
4. Zero-dependency regulatory rule comparison for a specific device model, producing standardized determination recommendations.

## How to use
Documentation-type tool; no scripts to run. The user describes device parameters and target standard numbers in natural language; the system retrieves and logically matches against the built-in official rule library. Results are structured as JSON IR for direct parsing.

## Workflow
1. Provide the device model and the non-clinical research scope to evaluate.
2. The system silently loads TH-MED-001 rules and matches across conditions.
3. Logical determination: validate research-stage attributes and experiment conditions against official definitions.
4. Generate JSON IR with conclusion, cited clauses, and risk analysis.
5. Parse the result and confirm it meets the zero-dependency output format.
6. Revise the R&D plan or adjust inputs to close the compliance loop.

## Evidence & safety
- Evidence: TBD; Version: 1.0.1; Security: no independent scan (TBD).

## 中文

# 医疗器械非临床研究判定器

## 何时用
1. 研发立项初期,依据 TH-MED-001 域规则快速判定研究阶段是否属于非临床研究范畴。
2. 临床/注册申报前,辅助验证已产生非临床数据的合规性与有效性。
3. 审查内部设计方案是否存在违反官方规则的非临床实验安排。
4. 针对特定型号器械做零依赖法规规则比对,生成标准化判定建议。

## 用法
文档型工具,无需调用脚本或安装插件。用户以自然语言描述器械参数与目标标准号,系统基于内置官方规则库检索与逻辑匹配;结果以 JSON IR 结构化输出,可直接解析集成。

## 流程
提供型号与评估范围 → 系统加载 TH-MED-001 规则并匹配 → 按官方定义做合规校验 → 生成含结论/引用条款/风险点的 JSON IR → 解析确认格式 → 修正研发计划或调整输入闭环。

## 证据与安全声明
- 证据:TBD;版本:1.0.1;安全:未做独立安全扫描(TBD)。

使用说明

# non-clinical-checker · 医疗器械非临床研究判定器

[![LGD](https://img.shields.io/badge/LGD-Governance-blue)](https://github.com/zhaoxinghua09-cell/lgd-theory)

> AI-assisted decision-support CLI. NOT legal advice, **not a compliance proof** — verify against official texts. Text verified: 2026-09-26.

## What it does
Derives the pre-market **non-clinical study checklist** per official rules: **GB/T 16886 系列(生物学评价)/ YY 0505(EMC)/ GB 9706.1(电气安全)** — based on `device_class` (I/II/III), `device_type` (active/passive/implant/ivd) and `contact` (surface/insert/implant).

- **Insufficient input → strict presumption**: when `device_type` / `device_class` / `contact` is missing, the tool states the possibly-missing studies (e.g. EMC, electrical safety, analytical performance) and the补参 suggestion in `warnings`, and sets `rc=1`. It never silently returns a lenient checklist.
- Invalid enum values are rejected (`rc=2`).
- **Out of scope**: full per-product test item set (must be derived from product technical requirements + risk management output), lab selection & scheduling, clinical evaluation route.

## Install & run (zero-dependency, Python 3.8+)
```bash
python non-clinical-checker.py --demo
python non-clinical-checker.py --device_class III --device_type implant   # rc=0
python non-clinical-checker.py --device_class II --device_type active     # missing contact → warnings, rc=1
python non-clinical-checker.py --device_class IV                          # invalid enum → rc=2
```

## Output
Deterministic JSON IR with `rc` (0=ok / 1=with warnings / 2=insufficient or invalid input), `required_studies`, `obligations`, `warnings`, `evidence`, and `aigc_mark` (GB 45438-2025 metadata, `is_generated: true`, label basis noted as pending verification). Decision support only — final determination rests with the regulator.

## Compliance & IP
- LGD-Powered badge · theory TH-MED-001 · ambassador 诺康@MED 域首席发声人
- 中文文档见 `SKILL.md`。本工具为决策支持,须人工复核,最终以监管机构认定为准。

---

## License & attribution
**分层许可(务必并读;代码许可不覆盖文档与理论文本)**

| 层 | 载体 | 许可 |
|---|---|---|
| 代码 | `non-clinical-checker.py` | **未在 LICENSE 中识别** |
| 文档与理论文本 | 本 `SKILL.md`、`README.md`、其中「理论依据」段与一切理论表述 | **不在代码许可覆盖范围内**:保留所有权利(All rights reserved) |

> 即:**代码可依其自身许可使用与再分发;文档与理论文本不因代码许可而默认可自由再发布。**

```
© 2026 SynomosAI. All rights reserved.
理论署名 (attribution) : LGD(Lifecycle Governance Doctrine / 全程治理论)— SynomosAI initiative
名称状态 (name status)  : "SynomosAI" — 未申请实体注册、未申请商标注册
                        (not a registered legal entity; no trademark registered)
生产参考部署 (production reference, self-reported) : 无(未声明外部生产参考部署)
                    ← 非认证、非背书、非监管认可(not a certification or endorsement)
代码许可 (code license) : 本包未附 LICENSE 文件(许可待定)
                    本文本与理论表述不在任何代码许可覆盖范围内
引用格式 (cite as)      : 本资产无 DOI
```
(上列为《LGD 对外表述规范》§3.2 统一块:**A 段公共段逐字复制、未删改;B 段资产参数段按本包真值填写**;发布 / 重提前须照最新版本复核。)

## 家族合集
| 环节 | 工具 | 大使 |
|---|---|---|
| 非临床研究 | non-clinical-checker | 诺康 |
| 上市后不良事件 | pms-vigilance-intake | 诺康 |
| 召回 | recall-decision-checker | 诺康 |
| 标签 | label-compliance-checker | 诺康 |
| 进出口 | import-export-router | 诺衡 |

如何安装此技能?

访问技能市场,点击「安装」按钮,按提示将技能包放入 AI 编程助手的 skills 目录即可。

浏览技能市场

支持平台:Qoder · QoderWork · Claude · Codex 等 AI 编程助手

Medical Device Non-clinical Research Checker - ¥0.10 | 技能派