Write a chart specification I can build in Excel or Power BI
A build-ready chart spec covering chart type, data mapping, scale, emphasis, labels, and accessibility for the message you need to show.
The prompt
Write a chart specification for my data so I or a colleague can build the chart correctly the first time.
Data: [PASTE TABLE or describe the columns, with units]
Message the chart must show: [e.g. "The West region drove most of the growth"]
Where it will appear: [PowerPoint slide / Excel report / Power BI or Tableau dashboard / printed report]
Audience: [WHO]
Tool: [Excel / Google Sheets / Power BI / Tableau / other]
Return a spec with:
1. Chart type and why it fits the message, plus one alternative.
2. Title: a takeaway headline stating the insight, and a subtitle with the metric, unit, and period.
3. Data mapping: X axis, Y axis, series, sort order, and any calculated fields with formulas.
4. Axes and scale: whether to start at zero (bar charts must), units, number format, gridlines.
5. Emphasis: which bar, line, or point to highlight, with a neutral color for everything else; any annotation or reference line (target, average, prior year).
6. Labels and legend: direct labels where possible, and what to label.
7. What to leave out: clutter to remove.
8. Accessibility: color-blind-safe contrast, readable font size, and meaning that doesn't rely on color alone.
9. Build steps for my tool, kept brief.
10. Footer note: source, date, and definitions.
If my data cannot support the message I gave, say so and suggest what the chart can honestly show. Don't add numbers that aren't in my data.
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
- PASTE TABLE or describe the columns, with units
- e.g. "The West region drove most of the growth"
- WHO
- Excel / Google Sheets / Power BI / Tableau / other
How this prompt is built
This prompt follows the RTF structure (Role, Task, Format). RTF tells the model who to be, what to do and what shape the answer should take. It is the quickest structure that still gives noticeably better results than a bare request.
Related prompts
- Write a data dictionary for a table or datasetProduces clear column-level documentation with definitions, types, allowed values, grain, and known caveats so others can use the data safely.
- Write up statistical results in proper reporting styleTurns software output into a correctly formatted results section with effect sizes, confidence intervals, and matching tables.
- Write commentary for a dashboard or KPI reportWrites the 'so what' narrative executives need alongside a dashboard — for sales, marketing, HR, finance, ops, or support.
- Write a SQL query from plain EnglishTurns a business question into SQL, with validation checks and an explanation.