# nasa-pra

The nasa-pra skill for Claude Code and Codex supports quantitative risk analysis of aerospace and safety-critical systems. Ask about fault trees, human reliability, or launch-abort scenarios.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · ★ 93 repo stars
- Author: jgsystemsconsulting
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/jgsystemsconsulting/jgs-se-knowledge-packs/tree/HEAD/packs/nasa-pra/SKILL.md
- Updated: 2026-11-04
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/nasa-pra

## What it does

The skill gives an agent material from NASA guidance for quantitative probabilistic risk assessment. It covers scenarios and consequences, event and fault trees, minimal cut sets, Bayesian parameter estimation, and uncertainty modeling. It also includes human reliability and software risk methods, plus worked launch-abort examples.

Load the core methods without an argument, or ask about a topic or chapter: `ch03` covers data and Bayesian estimation; `ch08` covers launch abort and worked examples. Supporting files include `glossary.md`, `patterns.md`, and `cheatsheet.md`. The material follows the 2011 second edition of the NASA guide and focuses on aerospace systems; qualitative RIDM and CRM decisions are handled by `nasa-risk`. Runtime needs are limited to Markdown files: no MCP server, API key, or paid tier is required.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add jgsystemsconsulting/jgs-se-knowledge-packs --skill nasa-pra -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add jgsystemsconsulting/jgs-se-knowledge-packs --skill nasa-pra -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add jgsystemsconsulting/jgs-se-knowledge-packs --skill nasa-pra -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install jgsystemsconsulting/jgs-se-knowledge-packs packs/nasa-pra/SKILL.md
```

2. **Manually: put the files in place**
- File: `.github/skills/nasa-pra/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add jgsystemsconsulting/jgs-se-knowledge-packs --skill nasa-pra -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/jgsystemsconsulting/jgs-se-knowledge-packs --path packs/nasa-pra
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add jgsystemsconsulting/jgs-se-knowledge-packs --skill nasa-pra -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/jgsystemsconsulting/jgs-se-knowledge-packs/tree/HEAD/packs/nasa-pra/SKILL.md

## When to use it
- build a quantitative model from risk scenarios
- decompose system failure into trees and minimal cut sets
- estimate human error probabilities
- model common-cause failures and uncertainty
- quantify a launch-abort scenario

## Example prompts
- Analyze the fault tree for this aerospace system.
- Assess human error in this scenario using NASA guide methods.
- Show how to model common-cause failure in this risk model.

## Similar
- [find-skills](https://affpapa.org/en/nevibecode/skills/find-skills.md) — skill · 4400000 installs
- [frontend-design](https://affpapa.org/en/nevibecode/skills/frontend-design.md) — skill · 1025790 installs
- [agent-browser](https://affpapa.org/en/nevibecode/skills/vercel-labs-agent-browser.md) — skill · 1600000 installs
- [design-taste-frontend](https://affpapa.org/en/nevibecode/skills/design-taste-frontend.md) — skill · 802600 installs
- [grill-me](https://affpapa.org/en/nevibecode/skills/grill-me.md) — skill · 1424476 installs
- [grill-with-docs](https://affpapa.org/en/nevibecode/skills/grill-with-docs.md) — skill · 1219756 installs

From the same set: [jgsystemsconsulting/jgs-se-knowledge-packs](https://affpapa.org/en/nevibecode/by/jgsystemsconsulting/jgs-se-knowledge-packs.md) — 60 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
