Open-source Agent Skills that teach AI agents (Claude Code, Cursor, and other skills-compatible agents) how to do useful data work with Tower: ingest enterprise data into a governed, open lakehouse built on Apache Iceberg, and delegate access to your team with Tower securely.
npx skills add tower/agent-skills
| Skill | What it does |
|---|---|
tower-integration |
Gets data into the lakehouse. Builds ingestion pipelines that land raw data from APIs, databases, SaaS tools, and files into Iceberg tables, then deploys and schedules them on Tower's managed compute. Credentials live in Tower secrets and never in code, config, or chat. |
tower-data |
Gets answers out of the lakehouse. Uses tower catalogs query — which vends a short-lived, read-only credential and runs SQL through DuckDB in one command — and answers questions with SQL you can audit. The agent never touches the source systems. |
Together they cover the full loop: source → governed lakehouse → answer. Tower sits in the middle, so every run has a status, history, and logs, and access is scoped and auditable.
You'll need a Tower account and the CLI:
pip install tower
tower login
npx skills add tower/agent-skillsThen ask your agent for what you want — "get our Stripe data into the lakehouse," "how many teams ran apps last week?" — and the right skill takes it from there.
Useful variants:
npx skills add tower/agent-skills --skill tower-data # just one skill
npx skills add tower/agent-skills -a claude-code # target a specific agent
npx skills add tower/agent-skills --list # see what's here firstIssues and pull requests are welcome. These skills are meant to improve through real use. See CONTRIBUTING.md for how to add a skill and AGENTS.md for the design principles every data skill here follows.
- Learn more about Tower
- Tower documentation
- Make Every Agent a Data Agent — the announcement post