Skip to main content

Skills setup

Prerequisites

  • Bauplan CLI installed with a configured API key
  • An AI assistant that supports MCP (Claude Code, Cursor, Claude Desktop)

Install Bauplan skills

Bauplan skills are distributed as a Claude Code plugin that installs with a single command and stays up to date automatically. For installation instructions, see the Bauplan Skills README.

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

SkillDescription
Data PipelineCreate a new pipeline project from scratch with proper setup, model definitions, source validation, and execution on a development branch.
Safe IngestionIngest 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 DataStructured, read-only investigation of lakehouse data through schema inspection, sampling, profiling, and join discovery. Produces a summary.md report.
Data AssessmentEvaluate whether a business question can be answered using lakehouse data. Maps concepts to tables, profiles quality, and delivers a feasibility verdict.
Data Quality ChecksGenerate quality check code as pipeline expectations (@bauplan.expectation()) and ingestion validation functions covering completeness, uniqueness, validity, freshness, consistency, and volume.
Debug and Fix PipelineStructured diagnostics for failed jobs: pins the failure, collects evidence, identifies root cause, and applies a minimal fix with checkpoint reports.

Skills can be used together with the MCP server or with repository-based usage (CLI/SDK only).

Source: https://github.com/BauplanLabs/bauplan-skills

Next steps

  • Learn more about the MCP Server for direct lakehouse access via tool calls