Data Quality Checker
Purpose
Use this skill when the user needs to know whether the dataset is trustworthy enough to continue.
When to Use
Use this skill when:
- Checking null rates, duplicates, invalid categories, or out-of-range values
- Verifying schemas after ETL or data ingestion
- Producing a pre-modeling data sanity checklist
Not For / Boundaries
- Rare-event or fraud detection: use
anomaly-detector - Model metrics and benchmark comparisons: use
evaluating-machine-learning-models - Report authoring and presentation polish: use
scientific-reporting
Typical Outputs
- Data quality scorecards
- Column-level issue summaries
- Recommended cleaning priorities before modeling or reporting
Related Skills
anomaly-detectorafter the basic data checks passstructured-content-storageif the dataset and outputs need stricter organization