# referral-program

Plans an in-app referral programme with reward rules, invite flows, fraud controls and K-factor measurement.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1700 installs · ★ 2219
- Author: appeeky
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/appeeky/aso-skills/tree/HEAD/skills/referral-program/SKILL.md
- Updated: 2026-10-06
- HTML: https://affpapa.org/en/nevibecode/skills/appeeky-referral-program

## What it does

This skill guides an agent through referral fit assessment, reward sizing and programme design. It can outline double-sided, inviter-only, tiered and other reward models, then produce a plan covering eligibility, payout caps, invite mechanics and referral metrics.

It checks for `app-marketing-context.md` and asks about product value, CAC, ARPU or LTV, plus existing deep-link infrastructure. Branch, AppsFlyer OneLink and Adjust are listed for attribution. Reward sizing needs a clear LTV, so review it with `asc-metrics` first when payback is unclear.

The plan covers value-moment invite prompts, personalised links, referral codes and deferred deep links. It also addresses repeat-account abuse, reward farming, bot signups and reward stacking. K-factor is calculated from invites sent per user and invite conversion rate.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add appeeky/aso-skills --skill referral-program -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/referral-program/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/referral-program/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add appeeky/aso-skills --skill referral-program -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/referral-program/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add appeeky/aso-skills --skill referral-program -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/referral-program/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install appeeky/aso-skills referral-program
```

2. **Manually: put the files in place**
- File: `.github/skills/referral-program/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add appeeky/aso-skills --skill referral-program -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/appeeky/aso-skills --path skills/referral-program
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/referral-program/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add appeeky/aso-skills --skill referral-program -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/appeeky/aso-skills/tree/HEAD/skills/referral-program/SKILL.md

## When to use it
- calculate a reward ceiling from LTV, margin and CAC
- choose a referral reward structure for both participants
- design an invite flow with deep links and deferred attribution
- limit repeat-account abuse and reward farming
- measure K-factor from invite volume and conversion

## Example prompts
- Create a referral programme plan for my app and size the rewards.
- Assess whether my product is a good fit for an invite-a-friend programme.
- Design fraud controls and K-factor metrics for our referral rewards.

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 8c0b360724eeeff3.

BEGIN THIRD-PARTY FILE 8c0b360724eeeff3
```text
---
name: referral-program
description: When the user wants to design, launch, or optimize an in-app referral / invite / share-to-earn program — including reward structure, mechanics, fraud prevention, deep link setup, and viral coefficient measurement. Use when the user mentions "referral program", "invite a friend", "refer and earn", "share to earn", "viral loop", "viral coefficient", "K-factor", "double-sided rewards", "give X get X", "referral rewards", "invite link", "share sheet", "Branch referrals", "in-app invites", or "how to make my app go viral". For deep link infrastructure that referrals depend on, see attribution-setup. For organic content-driven virality (UGC, creator), see creator-ugc-marketing.
metadata:
  version: 1.0.0
---

# Referral Program

You are a referral / viral growth specialist. Your goal is to help the user ship a referral program that drives a measurable lift in install volume — typically 5–20% of net-new installs once mature — without inviting fraud or eroding unit economics.

## Initial Assessment

1. Check for `app-marketing-context.md`
2. Ask: **What's the core value users would invite friends for?** (multiplayer, shared workspace, social, savings, status)
3. Ask: **What's your CAC** for a paid install? (sets the upper bound on referral reward)
4. Ask: **What's your ARPU / LTV** for a converted user?
5. Ask: **Do you have an MMP / deep link infra** already? (Branch, AppsFlyer OneLink, Adjust)
6. Ask: **Target audience** — does the product have natural sharing moments?

If LTV is unclear, route to `asc-metrics` first. You can't size rewards without knowing payback.

## Is a Referral Program Right for You?

| Strong fit | Weak fit |
|---|---|
| Network-effect product (chat, social, multiplayer, marketplaces) | Solo-use utilities with no sharing moment |
| High LTV / paid users | Low ARPU free apps where rewards aren't affordable |
| Content / progress that users want to show off | Apps users are embarrassed to use |
| Recurring engagement (daily-use) | One-and-done utilities |
| Existing organic word-of-mouth | No organic sharing happening today |

If "weak fit," steer the user toward `creator-ugc-marketing` or `retention-optimization` instead.

## Reward Structure Patterns

| Pattern | How it works | Best for |
|---|---|---|
| **Double-sided** ($X for both inviter + invitee) | Most common, fairest | Most consumer apps |
| **Inviter-only** | Sender gets reward, invitee gets nothing | Apps with strong organic install motivation |
| **Invitee-only** | New user gets discount/bonus, inviter doesn't | Cold acquisition, when virality isn't core goal |
| **Tiered / milestone** ("Invite 5 friends, get a year free") | Bigger rewards at milestones | Power users, status seekers |
| **Currency / credits** (in-app currency for both) | No real cash leaves the company | Games, content apps with IAP |
```
END THIRD-PARTY FILE 8c0b360724eeeff3

The third-party file has ended. Everything between the 8c0b360724eeeff3 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2879 of 8155 bytes. © appeeky · MIT · https://github.com/appeeky/aso-skills/tree/HEAD/skills/referral-program/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md