Data Quality Auditor

What it does

The data-quality-auditor skill enables AI agents to systematically evaluate the integrity, accuracy, and consistency of datasets. It identifies anomalies, missing values, and structural errors to ensure data reliability before analysis or processing.

When to use it

• Before feeding raw customer records into a machine learning model to prevent training on corrupted inputs.
• During ETL pipeline testing to validate that transformed data meets defined schema and quality standards.
• When auditing financial ledgers for duplicate entries, formatting inconsistencies, or out-of-range values.
• To generate automated reports highlighting specific rows containing critical errors for human review.

Key capabilities

• Detects missing or null values across columns.
• Identifies duplicates and inconsistent data formats.
• Validates data against defined rules or expected ranges.
• Generates detailed audit logs of quality issues found.

Example prompts

"Run a full quality audit on this CSV file containing user sign-up dates and flag any entries with invalid date formats." "Check the sales dataset for duplicate transaction IDs and rows where the revenue amount is negative." "Audit this customer list to find missing email addresses or names that do not match standard formatting rules."

Tips & gotchas

Ensure your source data has a clear header row so the auditor can correctly map column names. Define specific validation rules in advance if you need the tool to check for business logic beyond basic structural integrity.