decision-memo
Write a crisp decision memo that drives a clear decision, not a discussion. Use when asked to write a decision memo, a recommendation memo, a one/six-pager for a decision, or to get leadership to decide something. Produces a decision memo — the decision & recommendation up front, the context, options with trade-offs, what you'd need to believe, risks, and the explicit ask with a deadline.
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills /tmp/decision-memo && cp -r /tmp/decision-memo/plugins/pm-business/skills/decision-memo ~/.claude/skills/decision-memoSKILL.md
# Decision Memo Skill A decision memo exists to get a decision made — fast, on the record, by the right person. The failure mode is a memo that reads like a discussion: lots of context, no recommendation, no ask. This skill front-loads the recommendation and the decision being requested, then *supports* it — so the reader can say yes, no, or "here's my concern" in five minutes. ## Required Inputs Ask for these only if they aren't already provided: - **The decision** — the specific choice to be made (phrase it as a question with a yes/no or A/B/C answer). - **The recommendation** — your actual recommendation (a memo without one is a status update). - **The options** considered and their trade-offs. - **The decider & deadline** — who owns this call and by when. ## Output Format ### Decision Memo: [the decision] **To:** [decider] · **From:** [you] · **Date:** [date] · **Decision needed by:** [date] **1. Recommendation (TL;DR)** — the recommendation in 2–3 sentences, *first*. What you want them to approve, and the one-line why. **2. The decision** — the question being decided, framed so the answer is a clear choice. **3. Context** — the minimum background needed to evaluate it (link the rest). Why this is on the table now. **4. Options & trade-offs** — a table; be fair to the options you're not recommending (a stacked deck reads as one): | Option | Pros | Cons | Cost / effort | |---|---|---|---| **5. Why this recommendation** — the reasoning, and **what you'd have to believe** for it to be wrong (the assumptions it rests on). **6. Risks & mitigations** — the real downsides and how you'd handle them. A reversible decision deserves less agonising than an irreversible one — say which it is. **7. The ask** — exactly what you need from the reader: approve / pick an option / give input — by the deadline. ## Quality Checks - [ ] The recommendation is in the first paragraph, not the conclusion - [ ] The decision is framed as a clear question with a finite set of answers - [ ] Options not recommended are presented fairly, with real pros - [ ] The memo states what would have to be true for the recommendation to be wrong - [ ] It says whether the decision is reversible (one-way vs. two-way door) - [ ] There is an explicit ask and a decision deadline ## Anti-Patterns - [ ] Do not bury the recommendation at the end — the reader should know what you want in the first 30 seconds - [ ] Do not write a status update disguised as a decision memo — if there's no decision and no ask, it's not this document - [ ] Do not stack the options — strawman alternatives destroy your credibility and the decision's quality - [ ] Do not over-agonise a reversible decision — match the rigor to the cost of being wrong - [ ] Do not hide the assumptions — surfacing "what we'd need to believe" is what lets a decider pressure-test it ## Based On Narrative decision-memo practice (Amazon-style one/six-pagers; one-way vs. two-way door decisions).
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.