Referral Program logo

Referral Program

Organization
OpenClaudia
referral-program

Design referral programs and viral growth loops. Use when asked to create referral systems, viral mechanics, word-of-mouth campaigns, or growth loops. Trigger phrases: "referral program", "viral loop", "refer a friend", "word of mouth", "viral coefficient", "referral incentive", "growth loop", "invite system", "ambassador program".

Overview

PublisherOpenClaudia
Repositoryopenclaudia-skills
Skill namereferral-program
Stars
714
Forks
60
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Referral Program 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/OpenClaudia/openclaudia-skills/tree/main/skills/referral-program
  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/OpenClaudia/openclaudia-skills.git /tmp/openclaudia-skills
mkdir -p .claude/skills
cp -r /tmp/openclaudia-skills/skills/referral-program .claude/skills/referral-program
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Referral Program 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 Referral Program 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 Referral Program 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.

Referral Program Design

Design effective referral programs and viral loops that drive sustainable growth.


1. Referral Program Frameworks

One-Sided Incentives

Only the referrer gets rewarded.

Best for:

  • Products with strong organic word-of-mouth
  • Low-friction signups where the referred user needs no extra motivation
  • Cost-sensitive businesses

Examples:

  • Uber: "$10 credit for every friend you refer"
  • Amazon Associates: Commission on referred purchases

Template:

Refer a friend and get [reward].
Share your unique link: [referral_url]

Two-Sided Incentives

Both referrer and referred user get rewarded.

Best for:

  • Products requiring activation effort from new users
  • Competitive markets where new users need a nudge
  • Subscription businesses

Examples:

  • Dropbox: Both get 500MB extra storage
  • Airbnb: Referrer gets $25 credit, friend gets $40 off first stay
  • PayPal: Both get $10 when friend makes first transaction

Template:

Give [friend_reward], get [referrer_reward].
Share your link and you both win: [referral_url]

Tiered Incentives

Rewards increase with number of successful referrals.

Example tier structure:

ReferralsReward
1Free month
3Exclusive feature unlock
5Premium plan for 3 months
10Lifetime premium access
25Cash payout or swag box

Best for:

  • Creating power referrers / ambassadors
  • Products with passionate user bases
  • Building a referral leaderboard culture

2. Viral Coefficient Calculation

The viral coefficient (K-factor) determines whether your referral loop is self-sustaining.

Formula

K = i * c

Where:
  i = number of invites sent per user
  c = conversion rate of each invite

If K > 1: viral growth (each user brings more than one new user)
If K < 1: referrals supplement but don't replace other acquisition

Example Calculation

Users send an average of 5 invites (i = 5)
15% of invites convert to signups (c = 0.15)
K = 5 * 0.15 = 0.75

With 1,000 initial users:
- Cycle 1: 1,000 * 0.75 = 750 new users
- Cycle 2: 750 * 0.75 = 563 new users
- Cycle 3: 563 * 0.75 = 422 new users
- Total after 10 cycles: ~3,570 additional users from referrals

Viral Cycle Time

The speed of the viral loop matters as much as K:

Effective growth = K / cycle_time

A K of 0.5 with a 1-day cycle > K of 0.8 with a 30-day cycle

How to Improve K

LeverAction
Increase invites (i)Make sharing frictionless, prompt at key moments
Increase conversion (c)Better landing page, stronger incentive, social proof
Reduce cycle timeInstant reward delivery, real-time notifications

3. Referral Channels

Email Referral

Pros: High conversion, personal, trackable Cons: Lower volume, requires email access

Template:

Subject: I thought you'd like [Product] -- here's [reward] to try it

Hey [Name],

I've been using [Product] for [time] and it's been great for [specific benefit].

I wanted to share my referral link so you can get [friend_reward]:
[referral_url]

[Your name]

Social Media Sharing

Pros: High reach, low effort, viral potential Cons: Lower conversion rate, less personal

Platform-specific templates:

Twitter/X:

I just [achievement/milestone] with @Product! If you want to try it,
use my link and we both get [reward]: [referral_url]

LinkedIn:

I've been using [Product] to [professional benefit] and the results
have been impressive: [specific metric].

If you're looking for [solution], here's my referral link
(we both get [reward]): [referral_url]

WhatsApp/SMS:

Hey! I've been using [Product] and really like it. They have a
referral deal -- we both get [reward] if you sign up through my link:
[referral_url]

In-App Referral

Pros: Highest intent, contextual, frictionless Cons: Only reaches existing users

Best practices:

  • Show referral prompt after a success moment (completed task, achievement, positive outcome)
  • Pre-populate sharing message
  • Show referral progress and rewards earned
  • Add referral widget to account/settings page

Unique Link vs. Referral Code

MethodProsCons
Unique linkFrictionless, works in any channelHarder to share verbally
Referral codeEasy to remember, shareable verballyExtra step at signup
BothMaximum flexibilityMore complex to implement

4. Referral Landing Page Template

The page a referred user sees when they click the referral link.

Structure

[Hero Section]
- Headline: "[Referrer's name] invited you to [Product]"
- Subheadline: "Sign up now and get [friend_reward]"
- CTA button: "Claim your [reward]"

[Social Proof]
- "[Referrer's name] and X others use [Product]"
- Logos of known customers
- Key metric: "Trusted by X users"

[Value Proposition]
- 3 key benefits with icons
- Brief product description

[How It Works]
- Step 1: Sign up (takes 30 seconds)
- Step 2: [Key activation action]
- Step 3: Enjoy [reward] + the product

[CTA Repeat]
- "Join [Referrer's name] on [Product]"
- Urgency: "This offer expires in [X days]"

[FAQ]
- When do I get my reward?
- What does [Product] do?
- Is there a catch?

5. Case Studies

Dropbox (2008-2010)

  • Mechanic: Two-sided -- both get 500MB extra storage
  • Result: 3,900% growth in 15 months (100K to 4M users)
  • Key insight: The reward (storage) was the product itself, making it self-reinforcing
  • Viral coefficient: Estimated ~0.6-0.7 (supplemental, not purely viral)

Airbnb (2014)

  • Mechanic: Two-sided -- $25 travel credit for referrer, $40 off first booking for friend
  • Result: 300% increase in bookings from referral program 2.0
  • Key insight: Redesigned referral page to feel like a gift, not spam. Personalized with referrer's photo and travel history
  • Viral coefficient: Low K but high LTV per referred user

PayPal (1999-2000)

  • Mechanic: Two-sided -- $20 per referral (later reduced to $10, then $5)
  • Result: 7-10% daily growth, reaching 1M users in first year
  • Key insight: Cash incentive drove massive initial growth, then reduced as network effects kicked in
  • Cost: $60-70M in referral bonuses, but each user was worth much more in LTV

Robinhood (2014-2015)

  • Mechanic: Wait-list with move-up-the-line incentive + free stock for referrals
  • Result: 1M waitlist signups before launch
  • Key insight: Scarcity (waitlist) + social proof (your position) + tangible reward (free stock)

6. Implementation Checklist

Technical Setup

  • Generate unique referral links/codes per user
  • Build referral tracking (link clicks, signups, activations, rewards)
  • Set up attribution window (how long after click does signup count?)
  • Implement fraud detection (self-referral, fake accounts, VPN abuse)
  • Build reward fulfillment (automatic credit, manual approval, or hybrid)
  • Create referral dashboard for users (invites sent, pending, completed, rewards earned)

Fraud Prevention

  • Block self-referrals (same IP, same device, same email domain)
  • Require activation action before reward (not just signup)
  • Set daily/weekly referral limits per user
  • Flag suspicious patterns (bulk signups from same IP range)
  • Implement clawback for fraudulent referrals

Program Design Decisions

DecisionOptions
Reward typeCash, credit, product features, swag, charity donation
Reward timingOn signup, on activation, on first purchase
Reward amountTest multiple amounts; higher is not always better
ExpirationReferral links expire after X days? Rewards expire?
LimitMax referrals per user per month?
EligibilityAll users or only paid/active users?

7. Referral Email Sequences

Invite Reminder (to existing users)

Subject: You have [X] invites waiting

Hey [Name],

Did you know you can give your friends [reward] and get [reward] for yourself?

You've invited [0/N] friends so far. Share your link:
[referral_url]

Here's what [Product] users are saying:
"[Testimonial]" -- [Customer name]

Referred User Welcome

Subject: [Referrer] sent you a gift -- [reward] inside

Hey there!

[Referrer's name] thinks you'd love [Product], so they're giving you [reward] to try it.

[CTA: Claim your reward]

What is [Product]?
[1-sentence description]

What you'll get:
- [Benefit 1]
- [Benefit 2]
- [Benefit 3]
- Plus [friend_reward] from [Referrer's name]

This offer expires in [X] days.

Referral Success Notification

Subject: [Friend's name] just signed up -- you earned [reward]!

Great news, [Name]!

[Friend's name] accepted your invitation and signed up for [Product].
Your [reward] has been added to your account.

Keep sharing: you've referred [X] friends so far.
[referral_url]

[Show progress toward next tier if using tiered rewards]

8. Measuring Success

Key Metrics

MetricFormulaGood Benchmark
Participation rateUsers who share / total users15-25%
Shares per userTotal shares / participating users3-5
Click-through rateLink clicks / shares20-40%
Conversion rateSignups / link clicks10-25%
Viral coefficient (K)Invites * conversion rate0.3-0.7 typical
Viral cycle timeAvg days from invite to new user's first invite1-7 days
Referral revenueRevenue from referred usersTrack separately
CAC via referralReward cost / acquired usersCompare to paid CAC

A/B Tests to Run

  1. Reward amount ($10 vs $20 vs $50)
  2. Reward type (credit vs cash vs feature unlock)
  3. One-sided vs two-sided incentive
  4. Referral prompt timing (after signup vs after first success)
  5. Landing page copy (gift framing vs deal framing)
  6. Email subject lines for referral invites
  7. Social sharing copy variations

Frequently asked questions

What does the Referral Program AI skill do?

Design referral programs and viral growth loops. Use when asked to create referral systems, viral mechanics, word-of-mouth campaigns, or growth loops. Trigger phrases: "referral program", "viral loop", "refer a friend", "word of mouth", "viral coefficient", "referral incentive", "growth loop", "invite system", "ambassador program".

Why use Referral Program on TypingMind?

Because you install it once and use it with any model. Referral Program 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 Referral Program in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/OpenClaudia/openclaudia-skills/tree/main/skills/referral-program. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Referral Program?

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 Referral Program?

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

Is the Referral Program AI skill free?

Yes. It is published on GitHub by OpenClaudia 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 👇