answering-natural-language-questions-with-dbt

Answer natural language business questions by querying dbt semantic layers and models.

Updated Jul 3, 2025
One-click install
npx skills add https://github.com/memadore/snowflake-dbt-demo --skill answering-natural-language-questions-with-dbt-memadore
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: answering-natural-language-questions-with-dbt
Source: https://github.com/memadore/snowflake-dbt-demo/tree/main/.agents/skills/answering-natural-language-questions-with-dbt
Command: npx skills add https://github.com/memadore/snowflake-dbt-demo --skill answering-natural-language-questions-with-dbt-memadore

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables users to ask business questions in natural language and receive data-driven answers by leveraging dbt's semantic layer and data modeling capabilities.

Core Features & Use Cases

  • Semantic Layer Querying: Directly query metrics defined in a dbt semantic layer.
  • SQL Modification: Modify compiled SQL from the semantic layer for custom filtering or aggregations.
  • Model Discovery: Explore dbt models to write custom SQL when the semantic layer is insufficient.
  • Manifest Analysis: Analyze dbt project artifacts (manifest.json, catalog.json) for schema information when no semantic layer server is available.
  • Use Case: A marketing manager asks, "What were total sales last quarter?" This Skill would first try to answer using the semantic layer, and if not possible, it would explore dbt models or analyze project artifacts to construct and execute a SQL query.

Quick Start

Use the answering natural language questions with dbt skill to find out the total sales for the last quarter.

Frequently Asked Questions about answering-natural-language-questions-with-dbt

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I query dbt metrics using natural language?

To query dbt metrics using natural language, this Skill translates business questions into queries against the dbt semantic layer to retrieve data-driven answers.

Can I answer business intelligence questions by analyzing dbt project artifacts?

Yes, you can answer business intelligence questions by analyzing dbt project artifacts like manifest.json and catalog.json to extract schema information and construct SQL queries.

What is the best way to retrieve custom data when the dbt semantic layer is insufficient?

When the dbt semantic layer is insufficient, the best way to retrieve custom data is by discovering dbt models to write custom SQL, or by modifying compiled SQL for specific filtering.

Do I need a dbt semantic layer server to answer natural language questions with dbt?

You do not need a dbt semantic layer server to answer natural language questions; the Skill can analyze project artifacts and explore dbt models to construct SQL queries instead.

How does dbt model discovery work for custom SQL generation?

dbt model discovery for custom SQL generation works by exploring project models to understand available data structures, allowing the creation of tailored queries for business intelligence workflows.

What are the limitations of querying data through the dbt semantic layer?

A limitation of querying data through the dbt semantic layer is that it may lack custom filtering or aggregations, requiring SQL modification or dbt model exploration for complex answers.