reviewing-model

Compare generated dbt SQL/YAML against source, test spec, and standards.

3|Updated Feb 27, 2026
One-click install
npx skills add https://github.com/accelerate-data/migration-utility --skill reviewing-model
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: reviewing-model
Source: https://github.com/accelerate-data/migration-utility/tree/main/skills/reviewing-model
Command: npx skills add https://github.com/accelerate-data/migration-utility --skill reviewing-model

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Read-only quality gate for one generated dbt artifact set. Review written SQL/YAML against the source routine, approved test spec, and shared standards, then return exactly one ModelReviewResult.

Core Features & Use Cases

  • Compare generated SQL/YAML against the original source routine, the approved test spec, and the defined standards to ensure fidelity.
  • Return a single ModelReviewResult that encodes the overall verdict and any issues for generator feedback.
  • Use this skill in CI checks or human-in-the-loop review to prevent regressions in dbt model production.

Quick Start

Review the latest generated model set for a given project root and target, and return one ModelReviewResult.

Frequently Asked Questions about reviewing-model

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

FAQPage Schema
How do I review generated dbt models against source routines and test specs?

Review generated dbt models by comparing the SQL and YAML artifacts against the original source routine, approved test spec, and shared standards to ensure data pipeline fidelity and return a single ModelReviewResult.

What is a dbt model quality check and how does it prevent regressions in data pipelines?

A dbt model quality check performs a read-only review of generated SQL and YAML artifacts against defined standards to identify issues, preventing regressions in data pipeline production during CI checks or human-in-the-loop review.

Can I use a dbt artifact review for CI checks and human-in-the-loop workflows?

Yes, you can use this dbt artifact review as a read-only quality gate in CI checks or human-in-the-loop workflows to safely review generated models, catching fidelity issues before they reach production data pipelines.

What happens if prerequisite checks or required dbt artifacts are missing during a model review?

If a prerequisite check or required dbt artifact is missing, the model review returns an error instead of attempting a review, ensuring that incomplete data pipeline components are not falsely validated.

Does dbt model review work with both SQL and YAML generated files?

Yes, dbt model review works by comparing both generated SQL and YAML files against the source routine and approved test spec, returning exactly one ModelReviewResult that encodes the overall verdict and any issues found.

What's the best way to enforce shared standards when generating dbt models?

The best way to enforce shared standards is to run a read-only quality review that compares generated dbt SQL and YAML artifacts against the source routine and test spec, returning a ModelReviewResult for generator feedback.