Medical Device Vigilance Reporting Pathway Intake

技能文档

---
name: pms-vigilance-intake
title: "Medical Device Vigilance Reporting Pathway Intake"
slug: pms-vigilance-intake
display_name: 医疗器械不良事件报告路径判定器
display_name_en: Medical Device Vigilance Reporting Pathway Intake
version: 1.0.1
category: medtech-reg
author: SynomosAI
license: MIT
allowed-tools: Read, Glob, Grep, Bash, Write, WebFetch
description: 医疗器械不良事件报告路径判定器——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-002 域（医疗器械全链路）。
description_zh: "医疗器械不良事件报告路径判定器——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-002 域（医疗器械全链路）。"
description_en: "Medical device adverse-event reporting pathway determination tool: zero-dependency decision support with JSON IR output (domain TH-MED-002, full device chain)."
tags: [医疗器械, 合规, 判定器, TH-MED-002, pms-vigilance-intake, medtech-reg, 不良事件]
classification:
  skillhub: ["medtech-reg", "medical-device", "pharmacovigilance"]
  clawhub: ["productivity", "development"]
  iso_25010: ["Functional suitability"]
read_when:
  - 收到新提交的不良事件数据需自动判定法定报告路径
  - 多部门管辖的复杂事件初筛需按官方规则库合规分类
  - 需生成符合 JSON IR 标准、可被后续步骤直接解析的决策建议
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 Vigilance Reporting Pathway Intake

## When to use
1. When newly submitted adverse-event data arrives and its statutory reporting pathway must be determined.
2. For triaging complex events involving multi-department jurisdiction, classifying them against the official rule library.
3. When an automated flow needs JSON-IR-standard decisions parseable by downstream steps.

## How to use
Pure documentation tool; no local scripts. Pass structured adverse-event elements or a full report summary as input; the interface returns JSON IR with the recommended pathway and rationale.

## Workflow
1. Confirm the adverse-event data has been basic-validated and formatted.
2. Wrap the structured text as input into the skill node.
3. Trigger execution; the backend matches TH-MED-002 regulatory rules.
4. Inspect the returned JSON IR for the recommended pathway code and clauses.
5. Close the business loop or route for manual review.

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

## 中文

# 医疗器械不良事件报告路径判定器

## 何时用
1. 收到新提交的不良事件数据，需自动判定其法定报告路径。
2. 涉及多部门管辖的复杂事件初筛，需按官方规则库合规分类。
3. 自动化流程需生成符合 JSON IR 标准、可被后续步骤直接解析的决策建议。

## 用法
纯文档型工具，无需本地执行脚本。以结构化不良事件要素列表或完整报告摘要为输入，返回含推荐路径与判定依据的 JSON IR。

## 流程
完成数据基础校验与格式化 → 封装为输入参数 → 触发执行并匹配 TH-MED-002 规则库 → 查看 JSON IR 中推荐路径代码与条款 → 闭环或转人工复核。

## 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

# pms-vigilance-intake · 医疗器械不良事件报告路径判定器

[![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
Determines the individual adverse-event **reporting path and deadline** per official rules: **《医疗器械不良事件监测和再评价管理办法》(总局令 第1号)** — based on `severity` (death/serious/possible_serious/other, required) and `event_type` (fault/use_error/design_defect, optional).

- **Insufficient input → strict presumption**: `possible_serious` without `event_type` → warning that a design-defect event may also trigger recall/re-evaluation assessment (`rc=1`). It never silently treats a lenient path as final.
- Invalid enum values are rejected (`rc=2`) — garbage severity is NOT silently treated as "other".
- `trigger_recall=true` cases point to `recall-decision-checker` for the follow-up decision.

## Install & run (zero-dependency, Python 3.8+)
```bash
python pms-vigilance-intake.py --demo
python pms-vigilance-intake.py --severity death        # immediate report + recall trigger warning, rc=1
python pms-vigilance-intake.py --severity serious      # 20-day path, rc=0
python pms-vigilance-intake.py --severity garbage      # invalid enum → rc=2
```

## Output
Deterministic JSON IR with `rc` (0=ok / 1=with warnings / 2=insufficient or invalid input), `report_path`, `deadline`, `trigger_recall`, `warnings`, `evidence`, and `aigc_mark` (GB 45438-2025 metadata, `is_generated: true`). Decision support only — final determination rests with the regulator.

## Compliance & IP
- LGD-Powered badge · theory TH-MED-002 · 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 | `pms-vigilance-intake.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。