Skip to content
SkillModel-led800 tokens in use

north-star-metric

Defines a North Star Metric and 3-5 input metrics, after classifying the business as an Attention, Transaction or Productivity game.

28,201 stars on the repository MIT Licensephuryn/pm-skills · pm-marketing-growth/skills/north-star-metric
claude plugin marketplace add phuryn/pm-skills claude plugin install pm-marketing-growth@pm-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing north-star-metric costs

76tokens idle
800tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure16/25
  • Examples3/15
  • Output7/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity80
  • Maintenance76
  • Community60
  • Maturity32
  • Momentum40

north-star-metric walks the agent through choosing one customer-centric metric that reflects the value users get from your product. It first classifies the business into one of three games (Attention, Transaction or Productivity), then proposes a metric checked against seven criteria.

It finishes with three to five input metrics that are easier to move in the short term and feed the North Star, giving you a small metrics constellation to track.

What You Get

  • A classification of your business as an Attention, Transaction or Productivity game
  • One proposed North Star Metric checked against seven criteria
  • Three to five input metrics that drive the North Star
  • A rationale for how each criterion is met

Common Use Cases

  • Choosing a North Star for a new product before setting OKRs
  • Replacing a vanity or revenue metric with a customer-value metric
  • Preparing a leadership discussion on what the company should optimize
  • Breaking a headline metric into input metrics that teams can influence

What Makes It Unique

The skill anchors the choice in the three business games and a seven-point test: easy to understand, customer-centric, sustainable value, vision alignment, quantitative, actionable and leading indicator. It spells out what a North Star is and what it is not, which keeps revenue and LTV out of the answer. It links to the author’s North Star Framework 101 and related metric guides for deeper reading.

Under The Hood

A single SKILL.md of instructions and reference text, with no scripts. The agent works from the business context you describe and its own knowledge. The skill does not tell it to fetch web pages, call APIs, run commands or write files. The links at the end are reading material for you. Your business description replaces $ARGUMENTS in the prompt.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers