Create a data-quality checklist for a recurring report or dataset
A reusable pre-publish checklist with checks, formulas, pass thresholds, owners, and what to do when a check fails.
The prompt
Create a reusable data-quality checklist I can run every time before I publish or use this report or dataset.
Report or dataset: [NAME and what it's used for]
Sources feeding it: [e.g. "CRM export + finance system + a manual Excel tracker"]
How often it's refreshed: [daily / weekly / monthly]
Problems we've had before: [e.g. "missing region codes", "double-counted refunds", "late data from one country"]
Tool: [Excel / Google Sheets / Power BI / SQL]
Time I can spend on checks: [e.g. "15 minutes per run"]
Build the checklist in these groups:
1. Arrival and completeness: data is current, row counts are in the expected range, no missing periods or sources.
2. Uniqueness: no duplicate keys or double-counted transactions.
3. Validity: values in allowed ranges and formats, no placeholders.
4. Consistency: totals reconcile to the source system or the prior report; definitions unchanged.
5. Reasonableness: big moves vs. last period are explained before publishing.
6. Presentation: filters, dates, labels, and units are correct.
Return:
1. A checklist table: # | Check | How to do it (formula, query, or manual step) | Pass threshold | Owner | Time needed.
2. The 5 critical checks to run if I only have 5 minutes.
3. A short sign-off block: checked by, date, exceptions noted.
4. What to do when a check fails: who to notify and whether to hold the report.
Keep it practical, and rank checks by how costly the error would be if it got through. Build in the problems we've had before.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Data & Analysis prompts
What to fill in
- NAME and what it's used for
- e.g. "CRM export + finance system + a manual Excel tracker"
- daily / weekly / monthly
- Excel / Google Sheets / Power BI / SQL
- e.g. "15 minutes per run"
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Explain a dataset or report in plain business languageExplains what a dataset or report contains, what each column or metric means, and what it shows, in words anyone can follow.
- Find what my dashboard is not telling meReviews a dashboard for blind spots, missing comparisons, vanity metrics, and misleading views, and suggests what to add.
- Flag impossible or suspicious values in my dataChecks your data against logic and business rules for impossible, placeholder, and implausible values, and gives reusable validation rules.
- Clean and standardize spreadsheet data with a log of every changeCleans pasted spreadsheet rows, fixes formats and inconsistencies, and gives you a change log plus steps to repeat it in Excel.