Writing North Star Metrics logo

Writing North Star Metrics

Community
cnfeat
writing-north-star-metrics

Help users define their North Star metric. Use when someone is choosing their primary success metric, trying to align the team around a key measure, struggling with metric proliferation, or setting up their measurement strategy.

Overview

Publishercnfeat
Repositorytop-pm-skills
Skill namewriting-north-star-metrics
Stars
55
Forks
6
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by cnfeat on GitHub. Read the source before you install it.

Installation

Install the Writing North Star Metrics AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/cnfeat/top-pm-skills/tree/main/参考skill/lenny-skills-main%20(2)/lenny-skills-main/skills/writing-north-star-metrics
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Use it in TypingMind

Enable Writing North Star Metrics in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Writing North Star Metrics on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Writing North Star Metrics is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Writing North Star Metrics

Help the user define their North Star metric using frameworks and insights from 27 product leaders.

How to Help

When the user asks for help with North Star metrics:

  1. Understand the value - Ask what specific value the product delivers to users (not revenue or internal activity)
  2. Test for simplicity - Ensure the metric can be understood and discussed by anyone in the company
  3. Check for actionability - Confirm teams can actually influence this metric through their work
  4. Add guardrails - Help them identify countervailing metrics that prevent gaming

Core Principles

Measure value delivered, not captured

Itamar Gilad: "The North Star metric measures how much value we create for the market. WhatsApp measured messages sent because every message is incremental value. Airbnb used nights booked." Select a metric that tracks core utility provided to the customer, not business extraction.

Avoid lagging indicators

Jess Lachs: "Retention is a terrible thing to goal on. It's almost impossible to drive in a meaningful way in a short term. Find a short-term metric you can measure that drives a long-term output." Identify proxy metrics that are sensitive to experimentation and correlate with long-term goals.

Simple beats sophisticated

Jess Lachs: "If people understand it, if they have an intuition around it, if it's something people can talk about across the company, it's going to be a much better metric than your made up composite score that nobody understands." Avoid composite metrics with complex coefficients.

Measure from the customer's perspective

Jeff Weinstein: "What was the value we're trying to produce for the customer, and can we measure it from their perspective? We suggested 'companies with zero support tickets.'" Define metrics based on the absence of friction or the presence of success moments.

A high-level mission simplifies decisions

Hari Srinivasan: "Everything at LinkedIn is a very connected ecosystem, but decisions aren't difficult because we're all here to help people connect to economic opportunity." A clear company-wide mission serves as the ultimate tie-breaker for product decisions.

Name metrics evocatively

Jeff Weinstein: "Picking metric titles that make you feel something. 'Companies with zero support' - the brevity and customer mindset built into the chart name can become currency inside the company." Use simple, evocative names instead of technical database field names.

Codify definitions precisely

Manik Gupta: "Everyone will talk about the same metric but have different nuances. What is a daily active user? Pick a definition, instrument it, codify it. No confusion." Metrics only drive alignment when backed by precise definitions and accurate instrumentation.

Select a hard activation metric

Lauryn Isford: "An activation rate that falls in a lower percentage range, maybe 5-15%, is better than a high percentage because it means there's likely much higher correlation with long-term retention." High-bar activation metrics that few users reach are often more valuable.

Revisit periodically

Lauryn Isford: "A North Star metric should be a measure of what you plan to do. Revisit North Star metrics every 6-12 months to ensure they still align with business goals." Be willing to shift metrics if the strategy requires it.

Avoid revenue as North Star

Sean Ellis: "I think monthly purchases is great because it maps to value people are getting. Units of value from the customer perspective is more important than overall revenue." Revenue should be a product of doing things right, not the day-to-day guiding metric.

Questions to Help Users

  • "What specific moment represents a user getting value from your product?"
  • "Could a non-technical person in your company understand and discuss this metric?"
  • "Can teams actually influence this metric through their work in a quarter?"
  • "What would happen if you gamed this metric - what would break?"
  • "Does this metric measure value delivered to users or value extracted from them?"
  • "Is this a leading indicator or a lagging one that's hard to move?"

Common Mistakes to Flag

  • Revenue as North Star - Revenue is an outcome; focus on the customer value that drives it
  • Complex composite metrics - If you can't explain it simply, teams can't rally around it
  • Lagging indicators like retention - Find the leading metrics that predict retention
  • Gaming vulnerability - Add countervailing metrics to prevent optimization that hurts users
  • Undefined terms - 'Active user' means nothing until you codify exactly what counts

Deep Dive

For all 35 insights from 27 guests, see references/guest-insights.md

Related Skills

  • Setting OKRs & Goals
  • Defining Product Vision
  • Prioritizing Roadmap
  • Designing Growth Loops

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Writing North Star Metrics AI skill do?

Help users define their North Star metric. Use when someone is choosing their primary success metric, trying to align the team around a key measure, struggling with metric proliferation, or setting up their measurement strategy.

Why use Writing North Star Metrics on TypingMind?

Because you install it once and use it with any model. Writing North Star Metrics is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Writing North Star Metrics in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cnfeat/top-pm-skills/tree/main/参考skill/lenny-skills-main%20(2)/lenny-skills-main/skills/writing-north-star-metrics. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Writing North Star Metrics?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Writing North Star Metrics?

As many as you like. As long as a model supports skills, you can use Writing North Star Metrics with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Writing North Star Metrics AI skill free?

Yes. It is published on GitHub by cnfeat under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇