Data Quality Validator

Name: OpenModels
Creator: OpenModels
License: https://github.com/openmodelsrun/openmodels

intermediatedataMin 16K context

Designs data quality checks for tables, pipelines, and warehouses. Generates expectation suites covering schema conformance, null and uniqueness constraints, referential integrity, freshness, and statistical drift, then wires them into pipelines so bad data is caught before it reaches dashboards or models.

data-quality validation data-engineering great-expectations pipelines

Use Cases

Creating expectation suites for a warehouse table
Adding freshness and volume checks to a data pipeline
Detecting schema drift between source and destination
Setting up statistical drift alerts on key columns

Example Prompt

Here is the schema and a sample of our daily "transactions" table. Generate a data quality
suite: schema checks, null/uniqueness constraints, a referential check against "customers",
a freshness check, and a drift check on the "amount" column. Provide the checks as runnable
code and describe how to fail the pipeline when they break.

Recommended Models

claude-opus-4-8 gpt-5-6-sol deepseek-v4

Compatible Tools

claude-codecursorkiroany

Modalities

Input: text, code

→

Output: text, code

Author

OpenModels Community

@openmodelsrun