# sap-hana-cloud-data-intelligence Guides your agent through building graphs and pipelines in SAP Data Intelligence Cloud, writing operators and setting up replication from ABAP systems. - skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 643 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-cloud-data-intelligence/skills/sap-hana-cloud-data-intelligence/SKILL.md - Updated: 2026-10-21 - HTML: https://affpapa.org/en/nevibecode/skills/sap-hana-cloud-data-intelligence ## What it does The skill hands the agent a reference for SAP Data Intelligence Cloud work: creating and editing graphs, custom Gen1 and Gen2 operators, ABAP and S/4HANA integration, replication flows, ML scenarios in JupyterLab, and Data Transformation Language functions. It includes a table of common failures — a graph breaking after an operator swap usually means mixed generations in one graph. Subengines get their own section: Python 3.9, Node.js, C++, ABAP. Operators on the same subengine share one OS process, while crossing engines costs serialization, so grouping them early pays off. Replication flows come with delivery guarantees spelled out: at-least-once by default with possible duplicates, exactly-once when you UPSERT into a database. ABAP work needs Cloud Connector and a destination with credentials configured first, otherwise the connection never comes up. One caveat: the skill metadata is flagged as awaiting a refresh against primary sources, so product lifecycle status and live graph behavior deserve a separate check. That is a reason to verify rather than trust the hints outright. ## Install ### Claude Code (native platform) 1. **Skills CLI (Vercel)** ```bash npx skills add secondsky/sap-skills --skill sap-hana-cloud-data-intelligence -a claude-code ``` 2. **Manually: put the files in place** - File: `~/.claude/skills/sap-hana-cloud-data-intelligence/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/sap-hana-cloud-data-intelligence/ ### Codex 1. **Skills CLI (Vercel)** ```bash npx skills add secondsky/sap-skills --skill sap-hana-cloud-data-intelligence -a codex ``` 2. **Manually: put the files in place** - File: `.agents/skills/sap-hana-cloud-data-intelligence/SKILL.md` — For all projects use ~/.agents/skills/ ### Cursor 1. **Skills CLI (Vercel)** ```bash npx skills add secondsky/sap-skills --skill sap-hana-cloud-data-intelligence -a cursor ``` 2. **Manually: put the files in place** - File: `.cursor/skills/sap-hana-cloud-data-intelligence/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/ ### GitHub Copilot 1. **GitHub CLI** ```bash gh skill install secondsky/sap-skills sap-hana-cloud-data-intelligence ``` 2. **Manually: put the files in place** - File: `.github/skills/sap-hana-cloud-data-intelligence/SKILL.md` ### Gemini CLI 1. **Skills CLI (Vercel)** ```bash npx skills add secondsky/sap-skills --skill sap-hana-cloud-data-intelligence -a gemini-cli ``` 2. **Platform CLI** ```bash gemini skills install https://github.com/secondsky/sap-skills --path plugins/sap-hana-cloud-data-intelligence/skills/sap-hana-cloud-data-intelligence ``` ### Windsurf (Devin Desktop) **Manually: put the files in place** - File: `.devin/skills/sap-hana-cloud-data-intelligence/SKILL.md` — The legacy .windsurf/skills/ path still works ### OpenCode **Skills CLI (Vercel)** ```bash npx skills add secondsky/sap-skills --skill sap-hana-cloud-data-intelligence -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-cloud-data-intelligence/skills/sap-hana-cloud-data-intelligence/SKILL.md ## When to use it - wire operators into a graph with matching port types - write a Gen2 operator with error recovery and snapshots - set up a replication flow from S/4HANA into HANA Cloud - debug a graph that breaks when Gen1 and Gen2 operators mix - pick the right subengine for a Python or Node.js operator ## Example prompts - Build a graph in SAP Data Intelligence: Kafka source, transform, write to HANA Cloud - My graph fails after I swapped an operator — check generations and subengines - Set up a replication flow from an ABAP system to S3 with task filters ## Similar - [data-pipeline](https://affpapa.org/en/nevibecode/skills/data-pipeline.md) — skill · 4900 installs - [data-engineering](https://affpapa.org/en/nevibecode/plugins/data-engineering.md) — plugin · ★ 41729 - [etl-connector-strategy](https://affpapa.org/en/nevibecode/skills/etl-connector-strategy.md) — skill · 8000 installs - [ETL Pipeline](https://affpapa.org/en/nevibecode/skills/etl-pipeline.md) — skill · 4800 installs - [apache-airflow-orchestration](https://affpapa.org/en/nevibecode/skills/apache-airflow-orchestration.md) — skill · 2400 installs - [google-cloud-solution-agentic-ai-data-science-workflow](https://affpapa.org/en/nevibecode/skills/google-cloud-solution-agentic-ai-data-science-workflow.md) — skill · 5200 installs From the same set: [secondsky/sap-skills](https://affpapa.org/en/nevibecode/by/secondsky/sap-skills.md) — 24 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