agentsclimarketplace

Product metrics

Skill jpoindexter/product-management-skills/skills/product-metrics

Operational product-management skills and a /pm router for Codex and Claude.

Install
npx -y skills add jpoindexter/product-management-skills --skill product-metrics

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 15 days oldThe repository was created 15 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Define product success measures, metric trees, lifecycle metrics, guardrails, instrumentation requirements, and one decision-driving focus metric. Use when goals are vague, teams rely on vanity metrics, a roadmap lacks measures, or the user needs metrics tied to a business model and product stage.

SKILL.md

2.7 KB, 475 tokens by cl100k_base, as published. Nobody here has run it

Product Metrics

Select metrics that reveal whether the current product decision is producing durable customer and business value.

Inputs

  • Decision and owner
  • Product and business model
  • Target customer and lifecycle
  • Current company or product stage
  • Baselines, instrumentation, and known data quality issues
  • Expected behavior change and possible harms

Workflow

  1. State the decision the metrics must inform.
  2. Map the value mechanism from customer action to customer outcome to business outcome.
  3. Identify the current stage: problem empathy, stickiness, growth loop, revenue, or scale.
  4. Choose one focus metric for the current constraint and time horizon.
  5. Build a metric tree of controllable input metrics, intermediate behaviors, and lagging outcomes.
  6. Add guardrails for customer harm, quality, reliability, cost, and segment inequity.
  7. Define each metric precisely: event, population, numerator, denominator, window, exclusions, and owner.
  8. Audit instrumentation, missingness, identity resolution, and susceptibility to gaming.
  9. Set thresholds and the decision each result triggers.

Metric roles

  • Focus metric: current constraint the team intends to move
  • Input metric: behavior the team can influence directly
  • Outcome metric: customer or business result
  • Leading indicator: earlier signal with a validated relationship to the outcome
  • Guardrail: unacceptable side effect or boundary
  • Diagnostic: helps explain movement without defining success

Output contract

Return the decision, stage and business model, metric tree, focus metric, metric dictionary, guardrails, instrumentation gaps, thresholds, cadence, and owner.

Quality gate

  • The focus metric changes a decision.
  • A customer-value mechanism connects inputs to outcomes.
  • Cohorts and segments are visible where aggregates can mislead.
  • Guardrails protect against local optimization.
  • Metric definitions are reproducible.

Avoid

  • Total signups, page views, or cumulative volume without decision context
  • A universal north star detached from stage
  • Correlation presented as causal impact
  • Metrics the team cannot instrument reliably
  • Choosing many priorities to avoid choosing one

Source grounding

Operational synthesis informed by business-model, stage, cohort, vanity-metric, and One Metric That Matters concepts in Lean Analytics, plus outcome principles from Escaping the Build Trap.

Gives 0 of the 12 instructions most analytics metrics skills give in 475 tokens

Counted across 368 of the 369 authors here whose files we hold, read 2026-08-06

  • read product marketing context before asking questionsin 18 of 368, across 12 files
  • use lowercase with underscores for event namesin 16 of 368, across 6 files
  • track events for decisions not vanity metricsin 15 of 368, across 5 files
  • use object-action format for event namesin 15 of 368, across 8 files
  • produce a tracking plan documentin 14 of 368, across 4 files
  • Call RUBE_SEARCH_TOOLS first to get current schemasin 13 of 368, across 2 files
  • establish consistent event naming conventions before implementingin 10 of 368, across 4 files
  • Verify dimension and metric compatibility before reportingin 9 of 368, across 2 files
  • Encrypt data at rest and in transitin 9 of 368, across 3 files
  • use snake_case for event namesin 9 of 368, across 5 files
  • monitor technical health during the testin 9 of 368, across 5 files
  • use consistent property namesin 8 of 368, across 4 files

Said here and by no other author read

  • state the decision metrics must inform
  • map value mechanism from actions to outcomes
  • identify current product stage
  • choose one focus metric for current constraint
  • build metric tree from inputs to outcomes
  • add guardrails for harm and quality

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.