AI Skills

Skills are AI agent instructions installed into every RevOS project by revos init. Open Claude Code in your project and describe what you want in plain English — the agent picks the right skill automatically.

The skills live in the public revosai/skills repository — the single source of truth — grouped into bundles (one directory per bundle). revos init installs the data-engineering bundle into .claude/skills/ with the open skills CLI by pointing it at the bundle directory:

npx skills add revosai/skills/data-engineering --copy

--copy writes real files into .claude/skills/ (committable, no symlinks). Installing by bundle directory means that as the repo grows to hold bundles for other project types, a data-engineering project only ever gets the data-engineering skills. List a bundle's skills with npx skills add revosai/skills/data-engineering --list.

Keeping skills up to date

Because the skills are versioned independently of the CLI, you can refresh them in an existing project at any time — no re-init, no CLI upgrade:

npx skills update          # pull the latest into this project

If you work in the generated Dev Container, you don't even need to do that: it re-installs/refreshes the skills on every container start (best-effort) — installing the bundle if a prior attempt failed and updating it otherwise — so your skills stay current with revosai/skills automatically. Claude Code picks up the new files the next time it loads skills — no plugin install or reload.

To install only a subset of a bundle, name them with --skill:

npx skills add revosai/skills/data-engineering --skill explore-lakehouse create-cubes --copy

Using the skills with another agent

The skills aren't Claude-specific — the skills CLI can install them into any supported agent's directory. Name the agent(s) with -a:

npx skills add revosai/skills/data-engineering -a cursor --copy               # e.g. Cursor
npx skills add revosai/skills/data-engineering -a claude-code cursor --copy   # several at once
npx skills add revosai/skills/data-engineering --list                         # list the bundle's skills

The skills

The data-engineering bundle includes:

• explore-lakehouse
• create-connections
• create-cubes
• create-dbt-transformations
• load-sample-data
• query-semantic-model
• visualize-semantic-model

Each skill's full description, triggers, and instructions live with the skill in the revosai/skills repository — the single source of truth. Follow a link above to read its SKILL.md.