document-dbt

Name: document-dbt
Availability: InStock
Author: vnatarajan4061

Profile BigQuery tables and generate dbt source and model YAML documentation.

Updated May 4, 2025

Search Tags:#dbt #BigQuery #data documentation #schema metadata #BigQuery table profiling

Ready to run

npx skills add https://github.com/vnatarajan4061/phoenix --skill document-dbt

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: document-dbt
Source: https://github.com/vnatarajan4061/phoenix/tree/main/.claude/skills/document-dbt
Command: npx skills add https://github.com/vnatarajan4061/phoenix --skill document-dbt

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the documentation of dbt source and model YAML descriptions, ensuring AI-driven query generation accuracy and ground-truth data usage.

Core Features & Use Cases

Automated Documentation: Profiles BigQuery tables for schema metadata, sparse_ratio, and enum values.
Dataset Mode: Supports auto-discovery of all tables within a BigQuery dataset and parallel documentation.
Table/Model Mode: Documents specific tables or models in YAML files.

Quick Start

Use the document-dbt skill with the path to your dbt source or model YAML file, or specify a BigQuery dataset name to auto-discover all tables and document them in parallel.

Frequently Asked Questions about document-dbt

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

FAQPage Schema

How do I automate dbt documentation for BigQuery table schemas?▼

To automate dbt documentation for BigQuery, this Skill profiles your tables to extract schema metadata, sparse ratios, and enum values, then writes them directly into your source and model YAML files. It supports documenting specific tables or entire datasets.

Can I auto-discover and document all tables in a BigQuery dataset for dbt?▼

Yes, you can auto-discover and document all tables within a BigQuery dataset. By specifying the dataset name, the tool profiles all tables and generates the corresponding dbt YAML documentation in parallel.

Why does AI-driven query generation fail without ground-truth dbt schema metadata?▼

AI-driven query generation fails without ground-truth schema metadata because it lacks accurate column descriptions and data profiles. Automating dbt YAML documentation ensures AI queries use verified table structures, preventing hallucinated schemas.

What is the best way to generate dbt source YAML files from existing BigQuery tables?▼

The best way to generate dbt source YAML files from BigQuery is by profiling the tables for schema metadata and enum values. This tool automates that process, populating your YAML files with accurate data types and descriptions.

Does this dbt documentation tool support profiling sparse ratios and enum values?▼

Yes, profiling sparse ratios and enum values is supported. When documenting your dbt models, the tool queries BigQuery to capture these metrics and injects them into your YAML descriptions for better query accuracy.

Do I need to provide a dbt YAML file to document specific BigQuery models?▼

You need to provide the path to your dbt source or model YAML file to document specific tables. Alternatively, you can specify a BigQuery dataset name to auto-discover tables and generate the documentation automatically.