agentleFS
45ck45ck/marketing-product-skills/.agents/skills/north-star-metric/SKILL.md

north-star-metric

Skill3 starsChanged 8 months agoMITView on GitHub

Define or critique a product North Star Metric and its input metrics. Use when a team needs one shared leading indicator of customer value and growth.

17 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use brainstorm-okrs, positioning-ideas and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • skytiger6724Skill

    brainstorm-okrs

    Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.

    Also in 5 projects that use this

  • About-IntelligenceSkill

    positioning-ideas

    Brainstorm product positioning ideas differentiated from competitors.

    Also in 5 projects that use this

  • About-IntelligenceSkill

    gtm-motions

    Identify the best GTM motions and tools across 7 motion types: Inbound, Outbound, Paid Digital, Community, Partners, ABM, and PLG.

    Also in 5 projects that use this

  • skytiger6724Skill

    outcome-roadmap

    Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent. Rewrites initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps, making a roadmap more strategic, or rewriting feature lists as outcomes.

    Also in 5 projects that use this

  • miovragSkill

    strategy-red-team

    Red-team a PRD, roadmap, or strategy by attacking its load-bearing assumptions before reality does. Steelmans then attacks each claim, ranks failure modes by impact × likelihood × cheapness-to-test, and returns the cheapest test and kill criteria for each. Use when stress-testing a plan, pressure-testing a strategy, challenging assumptions, or preparing a doc for executive review.

    Also in 4 projects that use this

  • +3 more from About-Intelligence
  • +4 more from skytiger6724

The file

Show its rules and text

We split this skill into the rules it gives an agent

18 rules. 0 are common, 17 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 14 edited versions we read keep these.

  • 17

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user wants to define, refine, critique, or operationalize a North Star Metric (NSM) for a product, feature set, or …

    line 9
  2. Distinctive:

    Always produce these sections:

    line 13
  3. Distinctive:

    If the user asks only for critique, still use the same structure, but focus on diagnosing the existing North Star.

    line 26
  4. Distinctive:

    If the user or repo already provides them, extract:

    line 30
  5. Distinctive:

    If something is missing, make a best-effort assumption and label it clearly.

    line 43
  6. Distinctive:

    Prefer a leading indicator over lagging outcomes like revenue, MRR, or ARPU.

    line 47
  7. Distinctive:

    Prefer a metric that captures customer value realized, not vanity activity.

    line 48
  8. Distinctive:

    Prefer a metric that product and marketing can influence through day-to-day work.

    line 49
  9. Distinctive:

    Prefer one metric that is hard to game.

    line 50
  10. Distinctive:

    Avoid metrics that can rise while product value falls.

    line 51
  11. Distinctive:

    Avoid pure volume metrics when a quality threshold is required.

    line 52
  12. Distinctive:

    Avoid making the NSM directly editable by one team without the supporting system beneath it.

    line 53
  13. Very specific:

    Value exchange: When [user] does [meaningful action] to achieve [outcome], the business gains [business value].

    line 67
  14. Distinctive:

    If hybrid, pick the dominant one and explain why.

    line 76
  15. Distinctive:

    Create 3-6 input metrics that plausibly drive the NSM.

    line 104
  16. Distinctive:

    Write an implementation-ready spec with:

    line 118
  17. Distinctive:

    Use exactly this structure:

    line 144
  18. Distinctive:

    If you cannot recommend a single NSM with confidence:

    line 208

“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

North Star Metric

Use this skill when the user wants to define, refine, critique, or operationalize a North Star Metric (NSM) for a product, feature set, or business line.

What this skill must produce

Always produce these sections:

  1. Context summary
  2. Candidate engagement game / product motion
  3. North Star options (2-4 options)
  4. Recommended North Star
  5. Input metrics (3-6)
  6. Metric definition spec
  7. Why this is a good North Star
  8. Risks / failure modes
  9. Instrumentation requirements
  10. 30/60/90 day rollout plan

If the user asks only for critique, still use the same structure, but focus on diagnosing the existing North Star.

Inputs to gather

If the user or repo already provides them, extract:

  • Product name
  • Primary user
  • Primary customer / buyer
  • Core job-to-be-done
  • Core product motion: attention, transaction, productivity, or hybrid
  • Business model: freemium, self-serve, sales-assisted, enterprise, usage-based, seat-based, subscription
  • Core user actions
  • Desired business outcomes
  • Existing KPIs / dashboards / event schema
  • Whether this is company-level, product-line-level, or team-level

If something is missing, make a best-effort assumption and label it clearly.

Working rules

  • Prefer a leading indicator over lagging outcomes like revenue, MRR, or ARPU.
  • Prefer a metric that captures customer value realized, not vanity activity.
  • Prefer a metric that product and marketing can influence through day-to-day work.
  • Prefer one metric that is hard to game.
  • Avoid metrics that can rise while product value falls.
  • Avoid pure volume metrics when a quality threshold is required.
  • Avoid making the NSM directly editable by one team without the supporting system beneath it.

Step-by-step method

Step 1: frame the product and value exchange

State in one sentence:

  • who the user is
  • what they are trying to get done
  • what value the product creates
  • what value the business gets back

Use this format:

Value exchange: When [user] does [meaningful action] to achieve [outcome], the business gains [business value].

Step 2: identify the engagement game

Classify the product primarily as:

  • Attention: value comes from time, content consumption, expression, or repeated engagement
  • Transaction: value comes from completing purchases / bookings / exchanges with confidence
  • Productivity: value comes from completing a workflow more effectively or reliably

If hybrid, pick the dominant one and explain why.

Step 3: generate candidate North Stars

Create 2-4 candidate NSMs.

For each candidate provide:

  • metric name
  • formula
  • why it may work
  • why it may fail
  • what behavior it encourages
  • what anti-pattern it risks

Step 4: select the recommended NSM

Choose the best candidate and explain the tradeoff.

A recommended NSM should pass this checklist:

  • expresses customer value
  • represents product strategy
  • is a leading indicator
  • is actionable
  • is understandable
  • is measurable
  • is not a vanity metric

Step 5: define input metrics

Create 3-6 input metrics that plausibly drive the NSM.

For each input metric specify:

  • name
  • formula
  • owner
  • weekly directionality
  • why it matters
  • what team can influence it

Inputs should be operational levers, not just more outcomes.

Step 6: create the metric definition spec

Write an implementation-ready spec with:

  • canonical metric name
  • plain-English definition
  • numerator
  • denominator (if any)
  • quality thresholds
  • time window
  • aggregation level
  • exclusions
  • segment cuts
  • lagging outcomes expected to move if this improves

Step 7: stress-test the metric

Explicitly answer:

  • How could this metric be gamed?
  • Could it increase while user value falls?
  • What seasonal, cohort, or market distortions affect it?
  • What would make us revisit it?

Step 8: connect to instrumentation

List the minimum event and property requirements required to compute the NSM and each input metric.

Output format

Use exactly this structure:

Context summary

  • Product:
  • User:
  • Buyer:
  • JTBD:
  • Motion:
  • Business model:

Candidate engagement game / product motion

...

North Star options

OptionFormulaWhy it could workMain risk

Recommended North Star

Name:
Formula:
Interpretation:

Input metrics

Input metricFormulaOwnerWhy it matters

Metric definition spec

  • Canonical name:
  • Plain-English definition:
  • Grain:
  • Time window:
  • Quality threshold:
  • Included events:
  • Excluded events:
  • Segments to monitor:

Why this is a good North Star

  • Expresses customer value:
  • Represents strategy:
  • Leading indicator:
  • Actionable:
  • Understandable:
  • Measurable:
  • Non-vanity:

Risks / failure modes

  • ...
  • ...
  • ...

Instrumentation requirements

  • Events:
  • Event properties:
  • User properties:
  • Account / org properties:
  • Data quality checks:

30/60/90 day rollout plan

  • 30 days:
  • 60 days:
  • 90 days:

Failure mode handling

If you cannot recommend a single NSM with confidence:

  • say that directly
  • provide the top 2 candidates
  • explain the missing evidence needed to choose between them
  • recommend a temporary proxy metric and a validation plan

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.