# sap-hana-ml

This skill guides Python-based machine learning work with SAP HANA through hana-ml. Use it for in-database models, HANA DataFrames, AutoML, and model analysis.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 638 installs · ★ 475
- Author: secondsky
- License: GPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/secondsky/sap-skills/tree/HEAD/plugins/sap-hana-ml/skills/sap-hana-ml/SKILL.md
- Updated: 2026-10-21
- HTML: https://affpapa.org/en/nevibecode/skills/sap-hana-ml

## What it does

The skill covers database connections, DataFrame workflows, and PAL/APL methods for tasks such as classification, regression, clustering, and time-series analysis. It also walks through automated modeling, saving trained models, and inspecting results with visualizations and SHAP. DataFrame operations can build SQL before `collect()` runs, keeping processing in HANA rather than pulling large tables into Python.

The prerequisites are Python 3.8+ and SAP HANA 2.0 SPS03+ or SAP HANA Cloud; install the client with `pip install hana-ml`. PAL or APL algorithms will fail if the HANA system lacks the required AFL/PAL/APL libraries or licensing. The material also covers connection troubleshooting, splitting datasets, and assembling ML pipelines.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add secondsky/sap-skills --skill sap-hana-ml -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add secondsky/sap-skills --skill sap-hana-ml -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add secondsky/sap-skills --skill sap-hana-ml -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install secondsky/sap-skills sap-hana-ml
```

2. **Manually: put the files in place**
- File: `.github/skills/sap-hana-ml/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add secondsky/sap-skills --skill sap-hana-ml -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/secondsky/sap-skills --path plugins/sap-hana-ml/skills/sap-hana-ml
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add secondsky/sap-skills --skill sap-hana-ml -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/secondsky/sap-skills/tree/HEAD/plugins/sap-hana-ml/skills/sap-hana-ml/SKILL.md

## When to use it
- connect the `hana-ml` client to SAP HANA
- train and score an in-database PAL model
- run classification with APL AutoML
- persist a trained model with `ModelStorage`
- inspect model explanations with SHAP

## Example prompts
- Help me connect `hana-ml` to SAP HANA and load a table as a DataFrame.
- Build a PAL pipeline that fills missing values, normalizes features, and trains a classifier.
- Set up AutoML classification and save the trained model with `ModelStorage`.

## Similar
- [xlsx](https://affpapa.org/en/nevibecode/skills/xlsx.md) — skill · 187223 installs
- [google-agents-cli-observability](https://affpapa.org/en/nevibecode/skills/google-agents-cli-observability.md) — skill · 511300 installs
- [caveman-evidence-review](https://affpapa.org/en/nevibecode/skills/caveman-evidence-review.md) — skill · 104500 installs
- [migration](https://affpapa.org/en/nevibecode/skills/migration.md) — skill · 103900 installs
- [performance-optimization](https://affpapa.org/en/nevibecode/skills/performance-optimization.md) — skill · 65200 installs
- [supabase](https://affpapa.org/en/nevibecode/skills/supabase.md) — skill · 8 installs

From the same set: [secondsky/sap-skills](https://affpapa.org/en/nevibecode/by/secondsky/sap-skills.md) — 40 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