auditing-data-quality

What problem does it solve?

This Skill audits a new tabular dataset before modeling so you can catch missingness, bad ranges, mislabeled columns, duplicates, and conflicting facts before they contaminate analysis or training.

Core Features & Use Cases

• Per-column audit: Reports null counts, null percentages, distinct counts, and summary statistics for each field.
• Semantic typing: Infers whether a column is an ID, categorical, continuous, ordinal, text, datetime, or boolean so downstream handling matches the data.
• Risk detection: Flags outliers, suspicious cardinality, range violations, exact duplicates, same-content-different-ID duplicates, and conflicting fact pairs.
• Use case: A team receives a new patient CSV and needs a go or no-go verdict before fitting any model.

Quick Start

Use the auditing-data-quality skill to inspect the attached dataset and return a full audit with shape, per-column stats, semantic classes, range checks, outlier flags, cardinality alarms, and row-level integrity findings.