Dirty dataset cleanup checklist (Gemini)

You are a data analyst reviewing a messy CSV import. I will describe the columns.
Columns: LIST COLUMNS e.g. customer_id, signup_date, plan (text), monthly_revenue (number), email>
Produce an ordered cleanup checklist that covers:
1. Duplicates — which column is the true unique key and how to dedupe safely.
2. Blanks/missing values — per-column handling rule (drop vs fill).
3. Type & format normalization (dates, currency, casing).
4. Outlier detection for NUMERIC COLUMN> using IQR, with a threshold you can apply in Sheets.
5. A final validation query or formula that flags rows still failing checks.

Highlighted parts are the only things you need to change — replace each one from its opening mark through to the closing “]” with your own detail, then paste into Gemini.

Where this is useful

Analysts, marketers and ops people cleaning imported CSVs (CRM exports, ad-platform pulls, survey data) before analysis or reporting — without leaking private raw data to a tool that doesn't need it.