Agent skill

Referral Program Design

by mohitagw15856 in mohitagw15856/pm-claude-skills

Design a referral or viral-loop program that actually drives growth.

MITAuto-check passedMarketing & SEO

Install Referral Program Design

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill referral-program-design -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills referral-program-design --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/referral-program-design .claude/skills/referral-program-design && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
referral-program-design
GitHub stars
1.4k
Token cost
~1k tokens
SKILL.md length
503 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Design a referral or viral-loop program that actually drives growth.

  • Asked to design a referral
  • SKILL.md covers Required Inputs, Output Format, Quality Checks and Anti-Patterns, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Refer-a-friend program

What it does

Referral Program Design is an agent skill from mohitagw15856/pm-claude-skills. Design a referral or viral-loop program that actually drives growth. Use when asked to design a referral or refer-a-friend program, build a viral/invite loop, set referral incentives, turn happy users into a growth channel, or improve word-of-mouth growth. Produces a referral design — the loop mechanics, incentive structure (who gets what, when), the viral-math estimate (k-factor/cycle time), the unit-economics check, fraud guardrails, placement & messaging, and success metrics.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Marketing & SEO, covering Referral and retention marketing, Financial modeling and Product metrics. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked to design a referral
  • Refer-a-friend program
  • Build a viral/invite loop
  • Set referral incentives

Example prompts

  • “/referral-program-design”

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. 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 Design loads about 1k tokens when it runs. Until then it costs about 127 tokens; SKILL.md has 503 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~127
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 503 words, ~1,000 tokens.

Download SKILL.mdSave it as .claude/skills/referral-program-design/SKILL.md (or your agent's skills folder).
name
referral-program-design
description
Design a referral or viral-loop program that actually drives growth. Use when asked to design a referral or refer-a-friend program, build a viral/invite loop, set referral incentives, turn happy users into a growth channel, or improve word-of-mouth growth. Produces a referral design — the loop mechanics, incentive structure (who gets what, when), the viral-math estimate (k-factor/cycle time), the unit-economics check, fraud guardrails, placement & messaging, and success metrics.

Referral Program Design Skill

A referral program is a growth loop, not a coupon. It only compounds if each new user invites more than they cost and the cycle is fast. This skill designs the mechanics and incentives, then sanity-checks them with the viral math — because most referral programs fail not on creativity but on a k-factor below 1.

Required Inputs

Ask for these only if they aren't already provided:

  • Why users would share — the genuine reason (status, mutual benefit, the product is better with others).
  • Economics — the value of a new customer (so the incentive budget is grounded) and current organic word-of-mouth.
  • The moment of delight — when users are happiest (the best time to ask for a referral).
  • Goal — what the program must do (lower CAC, accelerate growth) and over what horizon.

Output Format

Referral Program: [product]

1. The loop — map it: a user does X → is prompted to invite → friend accepts → friend activates → becomes a referrer. Name every step; the loop is only as strong as its weakest conversion.

2. Incentive structure — who gets what and when it unlocks (one-sided vs. two-sided; reward on signup vs. on the friend's activation — gating on activation kills fraud and aligns value). Ground the reward in customer value.

3. Viral math — estimate k = invites sent × conversion rate, and the cycle time. State honestly whether k approaches/exceeds 1 (true virality) or simply lowers CAC (the common, still-useful case). Don't promise exponential growth from a k of 0.2.

4. Placement & messaging — where the ask appears (anchored to the delight moment, not signup), the share channels, and copy that gives the sharer a reason that makes them look good.

5. Fraud & abuse guardrails — self-referral and fake-account defenses, reward gating on real activation, and limits/velocity checks.

6. Metrics — share rate, invite→signup→activation conversion, k-factor, referred-user retention vs. baseline, and CAC of referred vs. paid.

Show full SKILL.md (196 more words)Show less

Quality Checks

  • The reward unlocks on the referred friend's activation, not just signup (aligns value, blocks fraud)
  • The viral math (k-factor + cycle time) is estimated honestly — including admitting when it's a CAC-reducer, not true virality
  • The ask is placed at a delight moment, not bolted onto signup
  • Fraud guardrails (self-referral, fake accounts, velocity limits) are specified
  • Referred-user retention is measured, not just signups (referred users can be low quality)

Anti-Patterns

  • Do not pay for signups instead of activations — you'll fund fraud and low-quality users
  • Do not claim virality from a k-factor below 1 — be honest that it's lowering CAC, which is still worth doing
  • Do not bolt the ask onto onboarding before the user has felt value — nobody refers a product they haven't experienced
  • Do not ignore the sharer's social risk — give them a reason that makes them look generous/smart, not spammy
  • Do not skip fraud guardrails — an ungated incentive is an arbitrage opportunity, not a growth loop

Based On

Viral-loop / referral practice — k-factor and cycle-time math, activation-gated two-sided incentives, and abuse-resistant design.

Example Trigger Phrases

  • "Design a referral."
  • "Build a viral/invite loop."
  • "Set referral incentives."
  • "Turn happy users into a growth channel."
  • "Improve word-of-mouth growth."

© mohitagw15856, 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-design of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Referral Program Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Referral Program Design compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Referral Program Design this skillmohitagw15856/pm-claude-skills1.4k—~1kAutomated safety check: PassMIT
28 Community Building Globalminhnv0807/ai-business-skills609—~3.6kAutomated safety check: PassMIT
Payram PayoutsPayRam/payram-mcp158—~4.2kAutomated safety check: PassNone
Startup Metrics Frameworkaiskillstore/marketplace43310 repos~293Automated safety check: PassNone
Startup Metrics Frameworkwshobson/agents40k—~2.5kAutomated safety check: PassMIT
Analytics Insightsindranilbanerjee/digital-marketing-pro8621 repos~6.5kAutomated safety check: PassMIT

Similar skills

  • 28 Community Building Global

    minhnv0807/ai-business-skills

    A skill your agent uses when a PERSONAL brand needs its OWN community — Skool, Mighty Networks, Discord, Circle, or Slack: a three-layer public, member, and inner-circle blueprint, seven-day…

    609 GitHub stars~3.6k tokensUpdated 28 days ago
    Marketing & SEOAuto-check passed
  • Payram Payouts

    PayRam/payram-mcp

    Send crypto payouts and manage referral programs with PayRam.

    158 GitHub stars~4.2k tokensUpdated 2 days ago
    Marketing & SEOAuto-check passed
  • Startup Metrics Framework

    aiskillstore/marketplace

    This skill should be used when the user asks about "key startup metrics", "SaaS metrics", "CAC and LTV", "unit economics", "burn multiple", "rule of 40", "marketplace metrics", or requests guidance…

    433 GitHub starsUsed in 10 repos~293 tokens
    Business, Finance & HRAuto-check passed
  • Track, calculate, and optimize key performance metrics for SaaS, marketplace, consumer, and B2B startups from seed through Series A, including unit economics, growth efficiency, and cash management.

    40k GitHub stars~2.5k tokensUpdated 5 days ago
    Business, Finance & HRAuto-check passed
  • Analytics Insights

    indranilbanerjee/digital-marketing-pro

    Design the analytics layer with script-backed benchmarks: KPI trees, report templates, MMM, cookieless.

    862 GitHub starsUsed in 1 repo~6.5k tokens
    Marketing & SEOAuto-check passed
  • Partner and Affiliate Programs

    tech-leads-club/agent-skills

    Designs partner, affiliate and integration programs, from recruiting the first partners to tuning commissions, for founders and go-to-market leads.

    7k GitHub stars~4k tokensUpdated yesterday
    Marketing & SEOAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Referral Program Design

What does Referral Program Design do?

Design a referral or viral-loop program that actually drives growth. Referral Program Design is an agent skill from mohitagw15856/pm-claude-skills. Design a referral or viral-loop program that actually drives growth.

When should I use Referral Program Design?

Referral Program Design fits situations like: asked to design a referral; refer-a-friend program; build a viral/invite loop; set referral incentives.

How do I install Referral Program Design in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill referral-program-design -a claude-code`. Or copy the skill folder (skills/referral-program-design in mohitagw15856/pm-claude-skills) into .claude/skills/referral-program-design in your project. Claude Code loads it when a task matches its description.

How do I install Referral Program Design in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill referral-program-design -a codex`. Or copy the skill folder (skills/referral-program-design in mohitagw15856/pm-claude-skills) into .agents/skills/referral-program-design in your project. Codex loads it when a task matches its description.

Can I use Referral Program Design in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill referral-program-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/referral-program-design, .gemini/skills/referral-program-design, .github/skills/referral-program-design and .opencode/skills/referral-program-design in your project.

What does Referral Program Design need to run?

SKILL.md names no scripts, command-line tools or credentials: Referral Program Design is instructions for the agent only.

Does Referral Program Design access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Referral Program Design safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Referral Program Design use?

Referral Program Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Referral Program Design use?

About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Referral Program Design?

Skills that share tags, products or a category with Referral Program Design: 28 Community Building Global (minhnv0807/ai-business-skills, 609 stars), Payram Payouts (PayRam/payram-mcp, 158 stars), Startup Metrics Framework (aiskillstore/marketplace, 433 stars) and Startup Metrics Framework (wshobson/agents, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Referral Program Design?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.