---
name: data-analysis-prompt-framework
description: "Turns a dataset and a business question into a precise analysis plan: the right methods, the metrics to compute, the charts to draw, and a summary shaped for the audience. Use when an analyst or manager has a dataset and a business question and needs a structured analysis with findings tailored to a stakeholder. Do not use for writing SQL or Pandas code or building a live dashboard. Related topics: data, analytics, analysis."
---

# Data Analysis Prompt Framework

Turns a dataset and a business question into a precise analysis plan: the right methods, the metrics to compute, the charts to draw, and a summary shaped for the audience.

## When to use

Use this skill when an analyst or manager has a dataset and a business question and needs a structured analysis with findings tailored to a stakeholder. Do not use it for writing SQL or Pandas code or building a live dashboard.

## Workflow

1. Ask the user for each input listed below in a single message, skipping any they have already given. Where options are listed, offer them, but accept other answers too.
2. Restate the decision the analysis informs and the metrics that answer it.
3. Check data quality (gaps, duplicates, outliers, definition changes) and record how each issue affects the result.
4. Run each chosen analysis type and state the method, the finding, and the confidence in it.
5. Match a visual to every finding and say what the reader should notice.
6. Write the summary for the stated audience, leading with the answer and ending with caveats and next steps.

## Inputs

- **Data type** (choose one: Sales data, Customer behaviour, Marketing metrics, Financial data, Survey results, Web analytics, Product usage, HR data, Other)
- **Data source** (free text, e.g. "Google Analytics or Salesforce or an Excel export")
- **Time period covered** (free text, e.g. "Last 90 days or Jan to Dec 2024")
- **Approximate record count** (free text, e.g. "5000 rows or 1M events")
- **The question to answer** (longer free text)
- **Key metrics** (longer free text)
- **Audience for the results** (choose one: Executives, Marketing team, Engineering, Investors, Myself)
- **Analysis types** (choose any: Descriptive statistics, Trend analysis, Cohort analysis, A/B test evaluation, Funnel analysis, Segmentation, Correlation analysis, Forecasting, Anomaly detection)
- **Preferred visuals** (choose any: Bar chart, Line chart, Heat map, Table, Scatter plot)
- **Report format** (choose one: One-page executive summary, Detailed report, Slide deck outline, Dashboard mockup)

## Output

A report in the chosen format: answer first, then data-quality notes, findings per method with visuals, caveats, and recommended next analysis.

## Prompt template

Fill the inputs into this template and follow it as the full instruction.

### Data Analysis Request

Plan and run the analysis described below.

- Data type: {{Data type}}
- Data source: {{Data source}}
- Time period covered: {{Time period covered}}
- Approximate record count: {{Approximate record count}}
- The question to answer: {{The question to answer}}
- Key metrics: {{Key metrics}}
- Audience for the results: {{Audience for the results}}
- Analysis types: {{Analysis types}}
- Preferred visuals: {{Preferred visuals}}
- Report format: {{Report format}}

Begin with data quality checks (missing values, duplicates, outliers, definition changes) and say how each would change the answer. Then run the selected analysis types against the question, stating the method, the finding, and how confident the data lets you be. Pick visuals that suit each finding and say what each shows. Lead the summary with the answer to the decision question, then supporting evidence, caveats, and the next analysis worth doing.

## Pitfalls

- Reporting correlations as causes when the data cannot support a causal claim.
- Skipping data quality checks, so a tracking change shows up as a trend.
- Writing for the analyst instead of the audience, burying the answer under method detail.
