Skills

Bauplan Skills are reusable, declarative workflow templates that guide an LLM through multi-step data engineering tasks using Bauplan. Each skill encodes the intent, constraints, and expected sequence of a workflow that is otherwise easy to get wrong, while still operating on the same Bauplan primitives: branches, runs, validation, and publish.

Skills are available at github.com/BauplanLabs/bauplan-skills and can be used in Claude Code, Codex, Cursor, and all major harnesses and IDEs. We recommend installing them from this repository to keep them automatically updated to the latest version.

Prerequisites

Bauplan CLI installed with a configured API key;
Any AI coding tool that supports skills.

Installation

Claude Code

Inside Claude Code, follow these steps:

Add the marketplace /plugin marketplace add https://github.com/BauplanLabs/bauplan-skills and restart Claude Code;
Open the plugin installer with /plugin. Then, select Browse and install plugins → select bauplan-skills → press Space to select bauplan → press i to install;
Restart Claude Code.

Codex

Inside Codex, run the skill installer pointing at the Bauplan skills directory:

$skill-installer https://github.com/BauplanLabs/bauplan-skills/tree/main/plugins/bauplan/skills

Codex will fetch and install the Bauplan skills automatically. Restart Codex once the installer completes.

To verify the installation, run /skills and select List skills.

Cursor

Go to Settings > Cursor Settings > Rules, Skills, Subagents.

From there you have two options:

If you already use Claude Code with Bauplan skills installed: enable the Include third-party Plugins, Skills and Other Configs toggle. Bauplan skills will appear automatically.
If you only use Cursor: in the Skills section, click New and prompt the agent to import Bauplan skills from:
```
https://github.com/BauplanLabs/bauplan-skills/tree/main/plugins/bauplan/skills
```

Available skills

Once installed, the following skills are available as slash commands:

Skill	Description
Data Pipeline	Create a new pipeline project from scratch with proper setup, model definitions, source validation, and execution on a development branch.
Safe Ingestion	Ingest data from S3 using the Write-Audit-Publish (WAP) pattern: data is loaded on an isolated branch, validated, and merged only after quality checks pass.
Explore Data	Structured, read-only investigation of lakehouse data through schema inspection, sampling, profiling, and join discovery. Produces a `summary.md` report.
Data Assessment	Evaluate whether a business question can be answered using lakehouse data. Maps concepts to tables, profiles quality, and delivers a feasibility verdict.
Data Quality Checks	Generate quality check code as pipeline expectations (`@bauplan.expectation()`) and ingestion validation functions covering completeness, uniqueness, validity, freshness, consistency, and volume.
Debug and Fix Pipeline	Structured diagnostics for failed jobs: pins the failure, collects evidence, identifies root cause, and applies a minimal fix with checkpoint reports.