# high-stakes-analytics-decision-lab

The high-stakes-analytics-decision-lab Claude Code skill checks data quality and chooses an analysis method to match the question. It runs for evidence-based reports and decision work that needs uncertainty bounds.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 103 installs · ★ 5 repo stars
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/data-skills/tree/HEAD/skills/high-stakes-analytics-decision-lab/SKILL.md
- Updated: 2026-10-09
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/high-stakes-analytics-decision-lab

## What it does

The skill checks a dataset for missing values, duplicates, leakage, and mismatched granularity before analysis. It selects a descriptive, diagnostic, predictive, or prescriptive route based on the question and the data. Critical failures stop the workflow; some cleaning steps need explicit approval.

The output is a report with source references, claim boundaries, and data lineage. A decision brief is produced conditionally. The manual Python setup uses `requirements.txt`; Docker is another installation option.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill high-stakes-analytics-decision-lab -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill high-stakes-analytics-decision-lab -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/high-stakes-analytics-decision-lab/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill high-stakes-analytics-decision-lab -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/high-stakes-analytics-decision-lab/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/data-skills skills/high-stakes-analytics-decision-lab
```

2. **Manually: put the files in place**
- File: `.github/skills/high-stakes-analytics-decision-lab/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill high-stakes-analytics-decision-lab -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/data-skills --path skills/high-stakes-analytics-decision-lab
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/high-stakes-analytics-decision-lab/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill high-stakes-analytics-decision-lab -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/reason-machines/data-skills/tree/HEAD/skills/high-stakes-analytics-decision-lab/SKILL.md

## When to use it
- check a dataset for missing values and duplicates
- catch data leakage before analysis
- choose an analytical method for a specific question
- create a source-backed report with stated limits
- prepare a brief for a decision

## Example prompts
- Check this dataset for quality issues and choose an analysis method.
- Analyze these data for a decision and produce a report with sources.
- Assess the predictive case and describe the data limitations.

## Similar
- [high-stakes-decisions](https://affpapa.org/en/nevibecode/skills/high-stakes-decisions.md) — skill · 573 installs
- [data-quality](https://affpapa.org/en/nevibecode/skills/data-quality.md) — skill · 770 installs
- [analytics-pipeline-orchestration](https://affpapa.org/en/nevibecode/plugins/analytics-pipeline-orchestration.md) — plugin · ★ 450 repo stars
- [analyze-data-quality](https://affpapa.org/en/nevibecode/skills/analyze-data-quality.md) — skill · 9 installs
- [taxonomy](https://affpapa.org/en/nevibecode/skills/taxonomy.md) — skill · 65800 installs
- [google-cloud-solution-agentic-analytics-spark-knowledge-catalog](https://affpapa.org/en/nevibecode/skills/google-cloud-solution-agentic-analytics-spark-knowledge-catalog.md) — skill · 5000 installs

From the same set: [reason-machines/data-skills](https://affpapa.org/en/nevibecode/by/reason-machines/data-skills.md) — 82 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
