executive-summary-generator
Executive Summary Generator
When to use
- A detailed analysis needs to be condensed to 1–2 pages for a senior audience
- An executive asks "what's the bottom line?" and a full report won't be read
- Preparing a board deck section that summarises a longer analytical workstream
- A recurring report needs to lead with the key message rather than data tables
- A decision needs to be made by end of day and the executive has 10 minutes
Process
- Extract the top 3–5 insights — go through the full analysis and identify only the findings that change or reinforce a decision. Filter out interesting-but-not-actionable findings. If you have more than 5 insights, you haven't prioritised yet.
- Quantify the business impact of each insight — every insight must carry a number: revenue at risk, cost saving, users affected, time to payback. Vague impact ("significant") does not belong in an executive summary. See
references/executive_communication.md. - Write a one-paragraph situation statement — explain why this analysis was done, what the question was, and why the timing matters. One paragraph, no jargon.
- Apply the pyramid principle — lead each insight with the conclusion ("Mobile churn is causing $800K ARR loss"), then the evidence, then the supporting detail. Never bury the finding at the end of a paragraph.
- State recommendations as specific actions — each recommendation must name what to do, who is responsible, what the expected outcome is, and by when. "Improve the app" is not a recommendation.
- Write the decision block — the final section names the explicit decision or approval the executive needs to give, the investment or resource required, the expected return, and the deadline. Use
assets/executive_summary_template.mdto assemble the document.
Inputs the skill needs
- The full analysis or report to be summarised
- Knowledge of the executive audience (role, priorities, decisions they're responsible for)
- Quantified business impact for each major finding
- Recommended actions already identified
- Format constraints (one page, two pages, specific slide count)
Output
references/pyramid_principle_guide.md— answer-first structure, BLUF writing, how to edit a bottom-up draft into top-downreferences/executive_communication.md— adapting tone, removing jargon, quantifying everything, avoiding hedge languageassets/executive_summary_template.md— 1–2 page template: situation, key insights (with impact), recommendations (with outcomes), decision needed
More from nimrodfisher/data-analytics-skills
dashboard-specification
Design specifications for effective dashboards. Use when planning new dashboards, improving existing ones, or documenting dashboard requirements before development starts.
30data-quality-audit
Comprehensive data quality assessment against business rules, schema constraints, and freshness expectations. Activate when validating data pipeline outputs before production use, auditing a dataset against defined business rules, or producing a quality scorecard for a data asset.
30root-cause-investigation
Systematic investigation of metric changes and anomalies. Use when a metric unexpectedly changes, investigating business metric drops, explaining performance variations, or drilling into aggregated metric drivers.
30query-validation
SQL query review for correctness, performance, and best practices. Activate when a query needs review before production use, shows unexpected results, or runs too slowly.
29segmentation-analysis
Customer/user segmentation with actionable insights. Use when identifying distinct customer groups, analyzing segment-specific behavior, profiling high-value segments, or testing segmentation hypotheses.
29data-narrative-builder
Build compelling data-driven narratives. Use when presenting analysis results, creating stakeholder reports, or transforming a set of findings into a story that drives a specific decision or action.
29