Create beginner Works with: Any AI

Cleaning a Messy Export Before Analysis

Checklist Has example

• 📊 Excel
• 📈 Google Sheets

Create a repeatable clean-up sequence.

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

Plan how to clean a messy data export in Excel. Description of the problems I see (merged cells, extra header rows, text dates, trailing spaces, mixed formats): [PROBLEMS]. Sample of the first rows: [SAMPLE_ROWS]. Tool options: [TOOLS].

Give me an ordered clean-up routine with a check after each step: keep the raw file untouched, unmerge and fill down, standardise headers, trim and clean text, convert dates and numbers, remove duplicates by a key I choose, and validate totals against the source. Provide formulas for each step and the Power Query equivalent in plain description, with a recommendation on which to use for repeated monthly files. Add a log table that records each change. Flag any step that could destroy information, and test the approach on five invented rows.

Add a short checklist for the final data check: row counts match, key columns have no blanks, totals reconcile to the source, and a sample of ten rows has been compared by eye.

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.

Routine (invented sales export)
1. Save raw file as 'raw_2026-05.csv', never edit it.
2. Remove 3 header rows; use row 4 as headers.
3. TRIM and CLEAN text; convert '12/05/2026' strings to dates (check day-month order).
4. Convert '1,200.50' text to numbers.
5. Remove duplicate order IDs (kept first).
6. Validate: sum of amount equals source total 84,310.
Change log: 14 duplicates removed; 6 dates fixed.
Validation table: Raw total 84,310; cleaned total 84,310; row counts raw 1,214, cleaned 1,200 after 14 duplicates; difference explained.

• excel