executive-summary
The executive-summary skill transforms longer documents into decision-focused summaries tailored for senior stakeholders. Use this skill when tasked with creating executive summaries, management briefs, one-pagers, or briefing papers where readers need conclusions upfront, structured findings for rapid comprehension, and clear recommendations requiring specific action. The skill delivers outputs formatted for rapid executive review within three minutes, structured with bottom-line conclusions first, evidence-based findings, and defined next steps.
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills /tmp/executive-summary && cp -r /tmp/executive-summary/plugins/pm-cross/skills/executive-summary ~/.claude/skills/executive-summarySKILL.md
# Executive Summary Skill Writes executive summaries that busy decision-makers actually read — front-loaded with conclusions, structured for skimming, ruthless about what to include. ## Required Inputs - **Source document or topic** (paste or describe) - **Audience** (CEO / board / investor / minister / client / committee) - **Decision or action needed** (what should the reader do after reading?) - **Length limit** (1 page / 2 pages / 500 words) - **Format** (formal report / slide / email / briefing paper) ## Core Principle An executive summary is NOT a summary of the document. It is a standalone document that: - States the conclusion upfront — not at the end - Contains only what the reader needs to make a decision - Can be understood without reading anything else - Recommends a specific action ## Output Structure --- ### [Title] **Executive Summary** *Prepared for: [Audience] | Date: [Date] | Author: [Name]* --- **Bottom line up front:** [The most important thing. The recommendation or finding. 2-3 sentences. A reader who only reads this should know what you are asking or telling them.] --- **Background (why this matters):** [2-3 sentences. Minimum context to understand the bottom line. Not the history — just what the reader needs now.] --- **Key findings / analysis:** - **[Finding 1]:** [One sentence — specific and evidence-based] - **[Finding 2]:** [One sentence] - **[Finding 3]:** [One sentence] --- **Options considered:** (include only if a decision is being presented) | Option | Benefit | Risk | Recommendation | |---|---|---|---| | [Option A] | [Benefit] | [Risk] | Recommended | | [Option B] | [Benefit] | [Risk] | Not recommended | --- **Recommendation:** [Specific. "We recommend [action] because [reason]. This will [outcome]." Not "we suggest consideration of options."] --- **Immediate next steps:** - [Action 1 — specific, with owner and date] - [Action 2] --- **Risks of inaction:** [What happens if the reader does nothing] **Full report:** [Reference to where the full document can be found] --- ## Adapting for Different Audiences **CEO/MD:** Lead with financial or strategic impact. 1 page. Make the decision binary. Ask in sentence one. **Board:** Lead with governance or risk. Frame against organisational objectives. State specifically what you need from them. **Investor:** Lead with return or opportunity. Specific numbers. 1 page. Anticipate "why now." **Minister/senior public sector:** Lead with public benefit or policy alignment. Include cost-benefit framing. **Client:** Lead with their problem. Show you understand before presenting recommendation. ## Quality Checks - [ ] Bottom line in first 3 sentences - [ ] Standalone — no need to read full document - [ ] Recommendation is specific - [ ] Fits length limit - [ ] Written for audience priorities not author priorities - [ ] Next steps have owners and dates ## Anti-Patterns - [ ] Do not summarise the document chronologically — an executive summary that follows the structure of the source document is not an executive summary, it is an abstract - [ ] Do not bury the recommendation at the end — executives read the first paragraph and skim the rest; the ask must be in sentence one or two - [ ] Do not use the same summary for different audiences — a CEO and a board member have different decision contexts and require different framing - [ ] Do not include background that the reader already knows — every sentence of background must earn its place by making the bottom line more actionable - [ ] Do not leave the "risks of inaction" section vague — a summary that does not quantify what happens if the reader does nothing removes the urgency needed for a decision ## Example Trigger Phrases - "Write an executive summary of this report: [paste]" - "Summarise this document for the board: [paste]" - "Create a one-pager from this proposal for the CEO" - "Turn these findings into an exec summary"
Conduct a structured ethical review of an AI or ML feature, model, or product. Use when preparing to deploy an AI system, assessing algorithmic risk, auditing a model for bias, or producing a responsible AI impact assessment. Produces a structured ethics review covering fairness, transparency, privacy, safety, accountability, and societal impact with a risk tier score, pre-deployment checklist, and prioritised mitigations.
Structure AI and ML product decisions with the rigour of any product decision. Use when building AI-powered features, evaluating LLM integrations, designing AI products, or assessing AI readiness. Produces a complete AI product canvas covering problem definition, model approach, data requirements, evaluation framework, UX design, responsible AI checklist, and launch monitoring plan.
Transform feature briefs into structured design briefs that give designers the context they need before opening Figma. Use when asked to write a design brief, create a design handoff, brief a designer on a new feature, or translate a PRD into design requirements. Produces a brief with user goal, emotional context, success criteria, constraints, edge cases, and out-of-scope boundaries.
Design statistically rigorous A/B tests and interpret experiment results. Use when asked to design an experiment, run an A/B test, calculate sample size, interpret test results, or assess whether an experiment was successful. Produces a complete experiment design with hypothesis, sample size, run time, success criteria, and risk flags — or a results interpretation with ship/iterate/kill recommendation.
Synthesises user signals from multiple research sources into a unified, weighted insight brief. Use when you have data from interviews, support tickets, NPS verbatims, app reviews, or sales calls and need to reconcile contradictions, surface the underlying need behind requests, or answer 'what are users really telling us'. Produces ranked insights with confidence ratings, source weighting rationale, divergent signal analysis by user segment, and a research gap identification section.
Structure a product data analysis, metric deep-dive, funnel analysis, or cohort study. Use when asked to analyse product metrics, investigate a drop in conversion, explain a data change to stakeholders, or find the root cause of a metric movement. Produces a structured analysis with question, root cause, confidence level, and recommended action.
Interpret product metrics against goals and surface actionable signals. Use when asked to analyse product health, review key metrics, investigate a performance issue, produce a health report, or assess product-market fit signals. Produces a structured health report with RAG status, trend analysis, root cause hypotheses, and prioritised actions.
Structure a retention analysis, churn investigation, or engagement deep-dive for any product team. Use when asked to analyse user retention, investigate churn, measure DAU/MAU, or build a retention improvement plan. Produces a retention snapshot with root cause hypotheses, aha-moment correlation, and prioritised interventions.