# risk-management-specialist

risk-management-specialist — a skill for medical device risk management under ISO 14971:2019: planning, hazard analysis, risk control and post-production monitoring.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 136 installs · ★ 1183 repo stars
- Author: borghei
- License: LicenseRef-MIT-Commons-Clause · policy=link-only · description only; the file stays with the author
- Source: https://github.com/borghei/Claude-Skills/tree/HEAD/ra-qm-team/risk-management-specialist/SKILL.md
- Updated: 2026-10-23
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/borghei-risk-management-specialist

## What it does

Walks a device through the ISO 14971:2019 process: risk plan, hazard identification, evaluation, control measures, residual risk and what happens after launch. AI/ML hazards get their own treatment — bias, drift, adversarial inputs — alongside IEC 81001-5-1 cybersecurity and supply chain exposure.

Reference documents load per task: the process itself, hazard-analysis techniques such as FMEA, FTA, HAZOP and use error analysis, report templates. The arithmetic comes from `scripts/risk_matrix_calculator.py`: a 5x5 probability-by-severity score, FMEA RPN from severity, occurrence and detection, or an interactive run.

It asks for the device and its intended use, the lifecycle stage and the acceptability criteria first. A risk number means little until the 5x5 thresholds and the ALARP definition are set. Software hazard analysis under IEC 62304 and penetration testing sit outside its scope.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill risk-management-specialist -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/risk-management-specialist/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/risk-management-specialist/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill risk-management-specialist -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/risk-management-specialist/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill risk-management-specialist -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/risk-management-specialist/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install borghei/Claude-Skills ra-qm-team/risk-management-specialist/SKILL.md
```

2. **Manually: put the files in place**
- File: `.github/skills/risk-management-specialist/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill risk-management-specialist -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/borghei/Claude-Skills --path ra-qm-team/risk-management-specialist
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/risk-management-specialist/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill risk-management-specialist -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/borghei/Claude-Skills/tree/HEAD/ra-qm-team/risk-management-specialist/SKILL.md

## When to use it
- Draft an ISO 14971 risk management plan for a new device
- Score risk on a 5x5 matrix and compute FMEA RPN
- Justify residual risk against ALARP
- Set post-production monitoring triggers for the risk file
- Fold cybersecurity and AI/ML bias into the hazard analysis

## Example prompts
- Score probability 3 against severity 4 with `scripts/risk_matrix_calculator.py`
- Run an FMEA hazard review for an infusion pump and build the risk register
- What should trigger a risk file review after launch?

## Similar
- [risk-management](https://affpapa.org/en/nevibecode/skills/risk-management.md) — skill · 2100 installs
- [risk-management-trading](https://affpapa.org/en/nevibecode/skills/risk-management-trading.md) — skill · 415 installs
- [operational-risk](https://affpapa.org/en/nevibecode/skills/operational-risk.md) — skill · 731 installs
- [portfolio-risk-management](https://affpapa.org/en/nevibecode/skills/portfolio-risk-management.md) — skill · ★ 8052 repo stars
- [risk-manager](https://affpapa.org/en/nevibecode/agents/voltagent-community-risk-manager.md) — subagent · 550 installs
- [design-fmea-generator](https://affpapa.org/en/nevibecode/skills/design-fmea-generator.md) — skill · 1 install

## Other versions with the same name
- [risk-management-specialist · alirezarezvani](https://affpapa.org/en/nevibecode/skills/risk-management-specialist.md) — 862 installs

From the same set: [borghei/claude-skills](https://affpapa.org/en/nevibecode/by/borghei/claude-skills.md) — 120 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
