domains / families / data / data-validate

data-validate

separate

Run declarative data quality checks and generate a codebook. Checks completeness, distributions, impossible values, duplicates, outliers, encoding issues, attention check failures, and manipulation check results. Produces a pointblank/pandera validation report and an auto-generated codebook. Use when the user says "validate data," "check data quality," "generate codebook," "what's wrong with my data," "data audit," "check my dataset," or when /research-intake identifies missing validation. Triggers on "validate," "data quality," "codebook," "check my data."

When to use

• validate data
• check data quality
• generate codebook
• data audit
• check my dataset
• check completeness
• check distributions
• check duplicates

When not to use

• data cleaning
• exploratory data analysis

Skill page

Source