Data Quality Audit Skill

Bad analysis usually starts with bad data nobody checked. This skill audits a dataset across the dimensions that matter, names the specific issues (and the exact check to confirm each), and prioritises fixes by how much they distort the answer.

Working from a brief

Given a dataset description, sample rows, or a schema, produce the full audit anyway — infer the likely issues for that kind of data and give the concrete check (SQL/pandas-style) to verify each. If given actual data, ground the findings in it. Never just say "check for errors"; specify them.

Required Inputs

Ask for (if not already provided):

• The dataset — schema, a sample, or a description (what each column is, the grain)
• What it'll be used for (the analysis/decision it feeds — focuses the audit)
• Source & freshness (where it comes from, how often it updates)
• Known issues the user already suspects

Output Format