OpenParable
Skip to content
← Back to skills

Great Expectations Generator

Testing & Quality

Great Expectations Generator is an Agent Skill for testing & quality published in the a5c-ai/babysitter repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Generates Great Expectations suites from data profiles and business rules

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/a5c-ai/babysitter/blob/HEAD/library/specializations/data-engineering-analytics/skills/great-expectations-generator/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/great-expectations-generator, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Great Expectations Generator

Overview

Generates Great Expectations suites from data profiles and business rules. This skill automates the creation of comprehensive expectation suites that enforce data quality constraints.

Capabilities

  • Expectation suite generation from profiling
  • Custom expectation creation
  • Checkpoint configuration
  • Data docs generation
  • Validation result analysis
  • Expectation parameterization
  • Suite versioning recommendations
  • Integration with dbt and Airflow

Input Schema

{
  "dataProfile": "object",
  "businessRules": ["object"],
  "existingSuite": "object",
  "strictness": "strict|moderate|lenient"
}

Output Schema

{
  "expectationSuite": "object",
  "checkpointConfig": "object",
  "documentation": "string",
  "coverageReport": {
    "columnsWithExpectations": "number",
    "totalExpectations": "number"
  }
}

Target Processes

  • Data Quality Framework
  • ETL/ELT Pipeline
  • dbt Project Setup

Usage Guidelines

  1. Provide data profile results from profiling analysis
  2. Define business rules that should be enforced
  3. Specify strictness level based on use case requirements
  4. Include existing suite if extending an existing configuration

Best Practices

  • Start with moderate strictness and adjust based on validation results
  • Include both column-level and table-level expectations
  • Document business rationale for each custom expectation
  • Version expectation suites alongside data transformations
  • Configure appropriate data docs for stakeholder visibility