metric-tree-builder
Decompose a north-star metric into a driver tree — the inputs and sub-inputs that actually move it — so a team knows which levers to pull. Use when asked to build a metric tree, break down a north-star metric, map metric drivers, or find the inputs behind an output metric. Produces a hierarchical tree from the top metric down to actionable input metrics, with the relationships, the highest-leverage levers, and what to instrument.
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills /tmp/metric-tree-builder && cp -r /tmp/metric-tree-builder/plugins/pm-data/skills/metric-tree-builder ~/.claude/skills/metric-tree-builderSKILL.md
# Metric Tree Builder Skill A north-star metric you can't decompose is a number you can't move. This skill breaks it into the multiplicative/additive drivers beneath it, down to metrics a team can actually act on — and points at the highest-leverage levers. ## Working from a brief Given a top metric and a rough business model, **build the full tree anyway**, inferring the standard driver structure for that model and marking assumptions. Never stop at one level; push down to input metrics someone owns. ## Required Inputs Ask for (if not already provided): - **The north-star / top metric** (e.g. weekly active revenue, MRR, GMV, activated users) - **Business model** (subscription, marketplace, ads, transactional, freemium) - **Where the team can act** (which teams own which surfaces) - **Current pain** (the metric is flat / dropping — optional, focuses the tree) ## Output Format ### 1. The decomposition Express the top metric as an equation of its drivers, e.g.: `Revenue = New customers × Avg first order + Retained customers × Repeat rate × AOV` Then break each driver down a level or two, until you reach **input metrics a team can directly influence** (e.g. signup conversion, activation rate, email open→click, time-to-value). Show it as an indented tree or a table: | Level | Metric | Driven by | Owner / lever | |---|---|---|---| | 0 | North star | — | | | 1 | Driver | sub-inputs | | | 2 | Input metric | actions | team | ### 2. Relationships Note where drivers are **multiplicative** (a small % gain compounds) vs **additive**, and any that trade off against each other. ### 3. Highest-leverage levers The 2–3 input metrics where a realistic improvement moves the north star most — and why (sensitivity × how movable it is). ### 4. Instrumentation gaps Which input metrics aren't being measured yet but should be, to make the tree usable. ## Quality Checks - [ ] The top metric is expressed as an actual equation of its drivers - [ ] The tree bottoms out in input metrics a team can act on, not more outputs - [ ] Multiplicative vs additive relationships are noted - [ ] Identifies the highest-leverage levers with reasoning - [ ] Flags metrics that need to be instrumented ## Anti-Patterns - A "tree" that's just a flat list of unrelated KPIs - Stopping at output metrics no one can directly move - Ignoring how drivers combine (treating everything as additive) - No view on which lever actually matters most
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.