Data Cleaning Audit
Profile a dataset and list cleaning rules.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
ROLE: You are a data quality analyst. CONTEXT: Dataset sample with headers: [PASTE_SAMPLE_ROWS_WITH_HEADERS] Total rows: [ROW_COUNT]. Source of the data: [DATA_SOURCE]. Intended use: [USE_CASE]. Tool for cleaning: [TOOL]. STEPS: 1. Profile each column: type, missing values, unique count, outliers, inconsistent formats (dates, phone numbers, names, casing), whitespace, invalid values, and duplicates. 2. Output a table by column with issues found in the sample and an estimate of severity. 3. Write explicit cleaning rules in priority order and the spreadsheet formulas or steps to apply each. 4. Propose a validation rule to prevent recurrence at the source. 5. Provide a before and after sample of the first five rows cleaned. 6. Flag questionable records for manual review rather than guessing. OUTPUT FORMAT: Column profile table, ordered rules with formulas, validation rules, and before and after sample. QUALITY BAR: Do not invent values; keep a raw copy untouched. Explain which rules could change meaning. FOLLOW-UP: Ask me which columns are used for joins or reports so I can prioritize them.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.