What problem does it solve?
Provides concise, actionable guidance and operational instructions for analytics engineering workflows with dbt so teams can build, test, validate, and troubleshoot data transformations reliably.
Core Features & Use Cases
- Model authoring & refactoring: guidance on writing SQL transformations, using ref() and source(), and applying DBT best practices.
- Unit tests & validation: create unit test YAML fixtures, run tests, and interpret run_results.json to prevent regressions.
- Semantic layer & metrics: author and validate semantic models and metrics for MetricFlow or legacy specs.
- Operational tooling & troubleshooting: format and run dbt CLI commands, configure dbt MCP servers, fetch dbt docs in LLM-friendly markdown, and diagnose dbt Cloud job failures.
- Use Case: Add a unit test for a model, validate semantic layer YAML, run a targeted build, and investigate any failing nodes with actionable next steps.
Quick Start
Ask the dbt skill to build and test the model named "orders" and return a summary of run_results.json with any failing nodes and suggested remediation steps.