Referral Program

What it does

When your agent uses it

• Wants to design
• Optimize an in-app referral / invite / share-to-earn program — including reward structure
• Fraud prevention
• Deep link setup

Example prompts

• “referral program”
• “invite a friend”
• “refer and earn”
• “/referral-program”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

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

What it can do on your machine

Read from SKILL.md and the folder at commit 3919d7c. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Referral Program loads about 2k tokens when it runs. Until then it costs about 174 tokens; SKILL.md has 777 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~174

When it runs · the whole SKILL.md, loaded when a task matches

~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from appeeky/aso-skills at commit 3919d7c, republished under its MIT licence (© appeeky). 777 words, ~2,018 tokens.

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

Max referral reward (per side) ≤ (LTV × target margin) - other CAC

K = (invites sent per user) × (conversion rate of invites)

REFERRAL PROGRAM PLAN — <App Name>

FIT ASSESSMENT: <strong / moderate / weak> — <reason>

REWARD STRUCTURE:
  Type: <double-sided / inviter-only / etc.>
  Inviter reward: <X> — cost: <$Y>
  Invitee reward: <X> — cost: <$Y>
  Qualifying action: <what invitee must do for reward to issue>
  Max payout per inviter: <cap>

EXPECTED ECONOMICS:
  Avg invites per active user: <est.>
  Invite conversion rate: <est. %>
  Projected K-factor: <est.>
  Cost per referred install: <$>
  Vs paid CAC: <better / worse / parity>

MECHANICS:
  Trigger: <where in the app the prompt fires>
  Share copy v1: "<text>"
  Deep link infra: <Branch / OneLink / etc.>
  Reward delivery: <instant / on qualifying action>

FRAUD CONTROLS:
  - <list>

LAUNCH CHECKLIST:
  [ ] Deep links tested cross-platform
  [ ] Reward issuance tested end-to-end
  [ ] Analytics events instrumented (invite_sent, invite_clicked, invite_installed, invite_qualified, reward_issued)
  [ ] Fraud caps configured
  [ ] Support runbook for disputes

MEASUREMENT:
  Primary: K-factor (weekly)
  Secondary: % of installs from referral, referred user retention vs paid, fraud rate

© appeeky, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/referral-program of appeeky/aso-skills.

Open the folder on GitHubat commit 3919d7c