Designing Growth Loops logo

Designing Growth Loops

Community
cnfeat
designing-growth-loops

Help users design and optimize growth loops. Use when someone is building viral mechanics, designing referral programs, creating product-led acquisition, or figuring out how to make their product grow itself.

Overview

Publishercnfeat
Repositorytop-pm-skills
Skill namedesigning-growth-loops
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 Designing Growth Loops 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/designing-growth-loops
  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 Designing Growth Loops 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 Designing Growth Loops 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 Designing Growth Loops 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.

Designing Growth Loops

Help the user design effective growth loops using frameworks from 54 product leaders who have built viral and product-led growth engines at companies from Dropbox to LinkedIn to Calendly.

How to Help

When the user asks for help with growth loops:

  1. Identify the loop type - Determine if they need viral, paid, content, or product-led acquisition loops
  2. Assess prerequisites - Check if they have the LTV, network effects, or product stickiness to support the loop
  3. Find the natural sharing moment - Help them identify where users would naturally want to bring others in
  4. Design for compounding - Ensure the loop feeds back into itself for sustainable growth

Core Principles

One dominant loop matters most

Luc Levesque: "It's usually just one loop that you need to get right. Most successful companies scale primarily through one dominant, well-executed growth loop." Focus on identifying and dominating one primary channel before diversifying.

Viral growth is a learnable science

Nikita Bier: "With certainty, if you're good at your job, you can make an app grow and go viral. Over the years of building all these apps, I've accrued all these growth hacks that still nobody knows about." Develop a library of growth tactics based on platform-specific mechanisms.

LTV unlocks paid loops

Yuriy Timen: "If you have really healthy LTVs, then there is a big opportunity to play paid and lean into paid growth loops." Calculate if single-player LTVs are high enough to support sustainable paid acquisition.

Product-led acquisition has zero marginal cost

Julian Shapiro: "By me trying to use PayPal in its everyday intention, I'm automatically enticing someone else to become a PayPal customer." PLA is the most scalable channel because it's entirely within the company's control.

Innovation over optimization in fast markets

Elena Verna: "I feel like only 30 to 40% of what I've learned transfers here because we need to invest in such bigger bets and innovate and create new growth loops." In fast-moving AI categories, shift from 95% optimization to 95% innovation.

Word-of-mouth requires frequency

Uri Levine: "Word-of-mouth you can only have if you have high frequency of use. If you're using Waze every day, then every day you have an opportunity to tell someone else." Sustainable word-of-mouth is tied to how often users engage with the product.

Map the loops qualitatively and quantitatively

Ben Williams: "Being able to identify the various micro and macro loops, how they're all connected, being able to document them in a qualitative model provides a shared understanding and guides intentional investment."

40-50% organic is the healthy ratio

Gokul Rajaram: "A good metric is that 40 to 50% of your new customers should ideally come from organic channels. If 90% come from paid, at some point the music is going to stop."

Questions to Help Users

  • "What's the natural moment when users would want to bring others in?"
  • "Does your product become more valuable when more people use it?"
  • "What percentage of your growth is organic vs paid?"
  • "What's your customer LTV and payback period?"
  • "Is there an action users take that automatically exposes your product to others?"
  • "Can you identify where users already share your product organically?"

Common Mistakes to Flag

  • Paid acquisition on freemium - Consumer subscriptions relying on paid acquisition will predictably fail
  • Manufacturing network effects - Network effects are usually inherent; hard to add as an afterthought
  • Diversifying too early - Early-stage companies should focus on one working engine
  • Single-channel dependency - Late-stage companies with 90%+ reliance on one channel are at extreme risk
  • Referral programs without organic WOM - Referrals amplify existing word-of-mouth; they can't create it

Deep Dive

For all 84 insights from 54 guests, see references/guest-insights.md

Related Skills

  • Measuring Product-Market Fit
  • Pricing Strategy
  • Retention & Engagement
  • Marketplace Liquidity Management

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 Designing Growth Loops AI skill do?

Help users design and optimize growth loops. Use when someone is building viral mechanics, designing referral programs, creating product-led acquisition, or figuring out how to make their product grow itself.

Why use Designing Growth Loops on TypingMind?

Because you install it once and use it with any model. Designing Growth Loops 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 Designing Growth Loops 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/designing-growth-loops. 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 Designing Growth Loops?

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 Designing Growth Loops?

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

Is the Designing Growth Loops 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 👇