← ClaudeAtlas

pmm-metricslisted

Defines a North Star Metric and 3-5 Input Metrics, then builds a capped 8-16 metric scorecard across Financial, Customer, Product & GTM, and Process & Growth, flagging vanity and unowned metrics. Trigger on: "what should we measure", "North Star metric", "build a PMM scorecard", "what metrics should I track", "define our key metrics", "set up a metrics framework".
stefanoskarakasis/Product-Marketing-Skills · ★ 13 · AI & Automation · score 86
Install: claude install-skill stefanoskarakasis/Product-Marketing-Skills
# PMM Metrics ## How This Works Picks one North Star Metric that predicts customer value and revenue, names the 3-5 Input Metrics that move it, then rounds out a scorecard across four categories (Financial, Customer, Product & GTM, Process & Growth), capped at 2-4 metrics per category — 8-16 total, small enough that a team actually updates it every 1-2 weeks instead of abandoning it by Q2. Every target and current value comes from the user — this skill doesn't invent numbers. If brain Section 2 (ICP/Beachhead) is loaded, it uses that to check whether a metric is a real leading indicator for the confirmed segment or just generic. Output is chat-only, disposable — the brain has no Metrics section to write to (all 6 existing sections are claimed), same treatment `experiment-ideas` (pmm-growth) gives its output. **Step 0** — Load brain Sections 1 (Product), 2 (ICP/Beachhead) if present, and guardrails from `/context/meta-patterns.md`. **Step 1** — Classify the business game: Attention, Transaction, or Productivity. **Step 2** — Define the North Star Metric and validate it against 7 criteria. **Step 3** — Define 3-5 Input Metrics that most directly move the North Star. **Step 4** — Build the supporting scorecard: 2-4 metrics per category across Financial, Customer, Product & GTM, and Process & Growth, each with a target, weight, and cadence. **Step 5** — Self-check the full set against sprawl and vanity-metric traps. **Step 6** — Deliver the scorecard as a markdown table