Referrals Word Of Mouth logo

Referrals Word Of Mouth

OrganizationPopular
RefoundAI
referrals-word-of-mouth

Help users build sustainable growth engines by transitioning from accidental word-of-mouth to structured referral programs and viral product loops.

Overview

PublisherRefoundAI
Repositorylenny-skills
Skill namereferrals-word-of-mouth
Stars
1.4K
Forks
175
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Referrals Word Of Mouth 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/RefoundAI/lenny-skills/tree/main/skills/referrals-word-of-mouth
  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.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git /tmp/lenny-skills
mkdir -p .claude/skills
cp -r /tmp/lenny-skills/skills/referrals-word-of-mouth .claude/skills/referrals-word-of-mouth
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Referrals Word Of Mouth 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 Referrals Word Of Mouth 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 Referrals Word Of Mouth 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.

Referrals and Word-of-Mouth

Turn user satisfaction into a high-leverage growth engine through organic advocacy and structured referral loops.

Help the user with referrals and word-of-mouth using insights from 13 guests and posts across Lenny's Podcast and Newsletter.

How to Help

  1. Assess readiness - Determine if the product has sufficient organic word-of-mouth and retention to support a formal referral program.
  2. Identify viral loops - Map out the product natural social actions to choose the right type of virality such as word-of-mouth, invitation, or experiential.
  3. Design incentives - Craft a reward structure that balances selfish, altruistic, and FOMO motivations within CAC limits.
  4. Optimize and scale - Measure the referral funnel and place touchpoints throughout the user journey to maximize discoverability.

Core Principles

Remarkableness as a Core Value

Rahul Vohra: "It is word of mouth. It is the virality you can't measure that isn't a mechanic that isn't in a feature. It is when one user spontaneously tells another user about your product."

Sustainable growth is earned through extraordinary quality and delight that makes a product worthy of spontaneous attention rather than temporary gimmicks.

The 10x Performance Threshold

Nilan Peiris: "But to get to recommendation, you're going to blow your user socks off. You have to give them an experience they didn't know was previously possible. And when you are in that place of doing something that no one has ever done before, that's when you get it."

To trigger true word-of-mouth, the product must be exponentially better than the status quo, typically by being significantly faster, cheaper, or easier to use.

Accelerate Existing Organic Growth

From "Building a referrals program": "The added incentive that a referral program offers simply adds fuel to an existing fire. I haven’t seen referrals work when there wasn’t strong existing WOM."

A referral program acts as an accelerator for existing interest. It should only be built once you verify that a majority of growth is already organic.

High-Value Milestone Incentives

From "Kickstarting supply in a labor marketplace": "Later, we had a two-sided referral program where if supply referred new supply, we would pay them $50 for each activated pro (after completing their first gig). If they referred a restaurant we would give them something like $300."

Structure referral payouts to occur only after the referred user reaches a clear activation milestone, such as completing their first transaction.

Product-Led Virality

Carilu Dietrich: "In order to get hypergrowth, you have to have organic, inbound, and viral word of mouth. You can't pay enough to grow at those rates and have a viable company."

Hypergrowth is driven by an amazing product experience that people are naturally excited to share, rather than unsustainable paid acquisition spend.

Community De-risking

Camille Ricketts: "In terms of how I think about what it actually is, it's when your community helps you achieve such ubiquity and such name recognition that it actually allows you to start moving upmarket into the enterprise. And I know that might be very specific to enterprise oriented companies, but that's how we defined it at Notion was the fact that so many people were talking about this, sharing what they had built about it, honestly starting businesses of their own around it to formalize the relationship with teams that I think it de-risked Notion as a choice for a lot of companies"

A passionate community creates brand ubiquity and user-generated social proof, which is critical for lowering perceived risk for new buyers.

Templates & Frameworks

  • Referral Program Readiness Checklist (Building a referrals program) - Five qualifying criteria to evaluate before investing in building a referral program. Use this to decide go/no-go.
  • Three-Phase Referral Program Build (Airbnb Model) (Building a referrals program) - Phased approach to building and scaling a referral program, based on how Airbnb evolved its host referral program from nascent to top growth driver.
  • Six Strategies to Increase Sharing Rate (How to increase virality) - Six distinct strategies for getting users to share your product more often, each with examples and 'How Might You' brainstorming prompts
  • K-Factor Virality Formula (How to increase virality) - The standard formula for measuring viral growth, measuring the number of new users each existing user drives
  • Referral Program Metrics Dashboard (Building a referrals program) - The key output and input metrics to track for a referral program, based on Airbnb's host referral program.
  • Seven Types of Virality Taxonomy (How to increase virality) - A classification system of seven distinct types of virality organized into three categories, each with real product examples
  • Purple Cow / Remarkability Test (Seth Godin) - A framework for evaluating whether your product has built-in word-of-mouth potential by being worth making a remark about.
  • Dropbox's Referral Program Growth (Generating buzz) - Dropbox's referral program offering free storage to both referrer and referee, contributing to growth from 100k to 4M users in 15 months

See references/artifacts.md for the full list with details.

Questions to Help Users

  • "What percentage of your current signups are coming from direct or organic search channels?"
  • "What is the core remarkable moment in your product that users would actually tell a friend about?"
  • "Is your product naturally multiplayer or does it provide more value when more people use it?"
  • "Have you identified the incentive plateau where increasing a referral reward no longer improves conversion?"
  • "How are you currently tracking 'How did you hear about us?' data during your onboarding?"
  • "Are your referral incentives aligned with a high-value user milestone or just a simple signup?"

Common Mistakes to Flag

  • Manufacturing virality from a mediocre product - If the core experience is not remarkable, synthetic loops and incentives will fail to create sustainable growth.
  • Misaligning referral incentives - Offering rewards that do not motivate users or that exceed the customer acquisition cost limits leads to inefficient spend.
  • Ignoring the supply side - Referral programs often provide more leverage on the supply side of a marketplace than the demand side, but are often overlooked.
  • Poor program discoverability - Burying the referral program in a settings menu instead of surfacing it at moments of high user satisfaction limits its volume.

Deep Dive

For all 36 sourced insights from 13 guests, see references/guest-insights.md

Related Skills

  • Growth Model
  • Acquisition Channels
  • User Onboarding Activation
  • Retention Engagement

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 Referrals Word Of Mouth AI skill do?

Help users build sustainable growth engines by transitioning from accidental word-of-mouth to structured referral programs and viral product loops.

Why use Referrals Word Of Mouth on TypingMind?

Because you install it once and use it with any model. Referrals Word Of Mouth 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 Referrals Word Of Mouth in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/RefoundAI/lenny-skills/tree/main/skills/referrals-word-of-mouth. 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 Referrals Word Of Mouth?

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 Referrals Word Of Mouth?

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

Is the Referrals Word Of Mouth AI skill free?

Yes. It is published on GitHub by RefoundAI 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 👇