Agent skill

Referral Program

by kostja94 in kostja94/marketing-skills

When the user wants to plan, implement, or optimize referral program strategy.

MITAuto-check passedMarketing & SEO

Install Referral Program

skills CLI
$ npx skills add kostja94/marketing-skills --skill referral-program -a claude-code

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

GitHub CLI
$ gh skill install kostja94/marketing-skills referral-program --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/kostja94/marketing-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/channels/partnerships/referral-program .claude/skills/referral-program && 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
GitHub stars
1k
Token cost
~1.5k tokens
SKILL.md length
636 words
Files
1
Skills in repo
102
Repo updated
First seen
Licence
MIT

At a glance

When the user wants to plan, implement, or optimize referral program strategy.

  • Works in 3 steps: Product type: SaaS, AI tool, subscription → User base: Size, engagement, retention → Goal: Signups, purchases, or both
  • Optimize referral program strategy
  • SKILL.md covers Initial Assessment, Referral vs. Affiliate vs.…, Reward Models and Mechanism Types, plus 9 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Referral Program is an agent skill from kostja94/marketing-skills. When the user wants to plan, implement, or optimize referral program strategy. Also use when the user mentions "referral program," "referral marketing," "user referral," "refer-a-friend," "word-of-mouth growth," "referral rewards," "referral tracking," "referral code," "referral incentives," or "viral loop." For referral landing copy, use landing-page-generator.

Its SKILL.md is about 1.5k 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 and Landing pages. The repository describes itself as: Agent Skills for Marketing — SEO, Social, Influencer & More. 160+ open-source skills for SEO, content, 40+ page types, paid ads, channels, and strategies. Add project context… The licence is MIT.

When your agent uses it

  • Optimize referral program strategy
  • The user mentions referral program
  • Referral marketing
  • Word-of-mouth growth

Example prompts

  • “referral program,”
  • “referral marketing,”
  • “user referral,”
  • “/referral-program”

Workflow steps

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

  1. Product type: SaaS, AI tool, subscription
  2. User base: Size, engagement, retention
  3. Goal: Signups, purchases, or both

What it can do on your machine

Read from SKILL.md and the folder at commit 8dd89c5. 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 1.5k tokens when it runs. Until then it costs about 95 tokens; SKILL.md has 636 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~95
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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 kostja94/marketing-skills at commit 8dd89c5, republished under its MIT licence (© kostja94). 636 words, ~1,477 tokens.

Download SKILL.mdSave it as .claude/skills/referral-program/SKILL.md (or your agent's skills folder).
name
referral-program
description
When the user wants to plan, implement, or optimize referral program strategy. Also use when the user mentions "referral program," "referral marketing," "user referral," "refer-a-friend," "word-of-mouth growth," "referral rewards," "referral tracking," "referral code," "referral incentives," or "viral loop." For referral landing copy, use landing-page-generator.
metadata.version
1.0.1

Channels: Referral

Guides referral program strategy for AI/SaaS products. Leverage existing users to drive growth; 3%-5% conversion vs 1%-2% for ads; CAC 50%-70% lower; referred users LTV 30%-50% higher, retention 20%-30% higher. Referral is necessity in overseas markets, not alternative.

When invoking: On first use, if helpful, open with 1-2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.

Initial Assessment

Project context: Read root contextus.md when present and load only the modules relevant to this task. Without Contextus, use available project material or user-provided facts and ask for missing information; do not create a parallel context system.

Identify:

  1. Product type: SaaS, AI tool, subscription
  2. User base: Size, engagement, retention
  3. Goal: Signups, purchases, or both

Referral vs. Affiliate vs. Influencer

DimensionReferralAffiliateInfluencer
WhoExisting usersProfessional promotersKOLs
IncentiveDiscounts, creditsCommissionFees, product
BarrierLow (all users)MediumHigh
Conversion3%-5%VariesVaries

Referral vs affiliate: Referral needs no landing page or application; integrated in dashboard. Affiliate requires landing page and approval.

Reward Models

ModelUse
Two-wayBoth referrer and referee get rewards; highest participation
One-wayOnly referrer rewarded; cost control
TieredRewards increase with referral count (e.g. $10 for 1-5, $15 for 6-10, $20 for 11+); incentivizes volume

Benchmark: Rewards typically 10%-30% of product price; ~11% off or ~$21 value; weak incentives = low participation. Triggers: signup, purchase, activation, or sustained use.

Mechanism Types

TypeUse
Link-basedUnique referral link; easy to implement; accurate tracking; share via email, social, SMS; works for web and app
Code-basedReferral code (e.g. FRIEND20); memorable; offline events; mobile-friendly input
Social referralShare buttons (Facebook, X, LinkedIn); viral spread; friend trust; young users

Tracking & Attribution

MethodUse
CookieWeb apps; 30-90 day window
URL paramsAll platforms; persistent in link
Referral codeMobile, offline; manual entry
Account associationLong-term tracking; subscription products

Attribution window: 30-90 days typical; 180 days for subscription. First-touch attribution to avoid double-counting.

Fraud Prevention

RiskAction
Self-referralDetect same device, payment, IP
Fake accountsValidate email, payment; monitor patterns
Bulk/automationRate limits; anomaly detection
Per-user cape.g. Max 10 referrals per user

Use tool anti-fraud features; audit referrals regularly.

Show full SKILL.md (260 more words)Show less

Design Framework

  1. Reward structure: Type (cash, discount, credits, free service); amount (10%-30% of price); trigger; cap
  2. Tracking: Choose method; set attribution window; first-touch rule
  3. UX: One-click share; clear rules; dashboard with referral data; notify on success
  4. Fraud prevention: See above
  5. Monitor & optimize: Referral rate, conversion, CAC, LTV; A/B test rewards and flow

Best Practices

  • Run multiple programs: Target different audiences, stages, goals
  • Tiered rewards: Motivate top performers; progressive incentives
  • Friction-free sharing: Mobile-friendly; one-click share
  • Time-boxed incentives: "Refer this week for $15 off" creates urgency
  • Placement: Web, email, app, in-product touchpoints; dashboard integration primary

Implementation

ApproachUse
Self-buildFull control; low cost; URL params or cookie + reward logic + fraud checks; open-source (e.g. RefRef) for faster start
Third-partyFast launch; Cello, Viral Loops, ReferralCandy (e-commerce), Impact (enterprise); monthly fee

Placement: Most programs integrate in product dashboard; no landing page or application needed. Optional landing page for value prop, rewards, and case studies.

Startup cost: Typically hundreds for tools + dev.

Tools

ToolUse
CelloSaaS; AI-driven automation
Viral LoopsReferral + waitlist + contests
ReferralCandyShopify, e-commerce
ImpactEnterprise; unified platform
RefRefOpen-source; self-hosted

KPIs

Referral rate, conversion, CAC, LTV of referred users, referred-user retention.

Output Format

  • Reward model and mechanism type (link/code/social)
  • Tracking approach and attribution window
  • Placement (dashboard vs landing page)
  • Fraud prevention measures
  • Tool selection (self-build vs third-party)
  • KPI framework
  • discount-marketing-strategy: Referral rewards (discounts, credits); 10–30% benchmark; campaign design
  • affiliate-marketing: Different audience; can run both
  • influencer-marketing: Brand building vs. user-driven growth
  • directory-submission: Directory submission for discovery; referral for user-driven growth
  • analytics-tracking: Referral link tracking, UTM

© kostja94, 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/channels/partnerships/referral-program of kostja94/marketing-skills.

Open the folder on GitHubat commit 8dd89c5

Compare with similar skills

Referral Program 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Referral Program this skillkostja94/marketing-skills1k—~1.5kAutomated safety check: PassMIT
Suede PaywallsJasonColapietro/suede-creator-skills127—~1.6kAutomated safety check: PassMIT
Ad Creative Builderaaron-he-zhu/aaron-marketing-skills2.9k2 repos~2.2kAutomated safety check: PassApache-2.0
Ad Library TeardownScrapeCreators/social-media-research-skills3.3k—~947Automated safety check: NotesMIT
Cro Optimizationognjengt/founder-skills406—~2.4kAutomated safety check: PassMIT
Autoresearchericosiu/ai-marketing-skills3.6k2 repos~2.2kAutomated safety check: PassMIT

Similar skills

  • Suede Paywalls

    JasonColapietro/suede-creator-skills

    Suede-affiliated in-product monetization design for paywall screens, feature gates, trial-expiry states, usage-limit prompts, and free-to-paid upgrade moments.

    127 GitHub stars~1.6k tokensUpdated 3 days ago
    Marketing & SEOAuto-check passed
  • Ad Creative Builder

    aaron-he-zhu/aaron-marketing-skills

    A skill your agent uses when the user asks to "write ad copy", "generate RSA headlines", or "build ad creative at volume"; produces ad units — RSA headlines/descriptions, hooks, and an angle matrix…

    2.9k GitHub starsUsed in 2 repos~2.2k tokens
    Marketing & SEOAuto-check passed
  • Ad Library Teardown

    ScrapeCreators/social-media-research-skills

    A skill your agent uses when the user wants to analyze active ads from Meta/Facebook, Google, or LinkedIn ad libraries; tear down a competitor's messaging; extract hooks, offers, CTAs, video…

    3.3k GitHub stars~947 tokensUpdated 1 mo ago
    Marketing & SEOAuto-check: notes
  • Cro Optimization

    ognjengt/founder-skills

    Analyzes landing pages and provides detailed CRO (Conversion Rate Optimization) recommendations.

    406 GitHub stars~2.4k tokensUpdated 4 mo ago
    Marketing & SEOAuto-check passed
  • Autoresearch

    ericosiu/ai-marketing-skills

    Run Karpathy-style autoresearch optimization on any content.

    3.6k GitHub starsUsed in 2 repos~2.2k tokens
    Marketing & SEOAuto-check passed
  • Afa Convert

    afadtc/afa-dtc-skills

    DTC 全链路转化率优化引擎——转化漏斗分析、结账流程优化、弃单挽回、落地页优化、A/B测试、信任元素。Use when user mentions: 转化率, conversion rate, CRO, 加购率, add to cart, 结账, checkout, 弃单, abandoned cart, 落地页, landing page, A/B测试, 信任度, trust, 购买流程…

    168 GitHub stars~1.8k tokensUpdated 9 days ago
    Marketing & SEOAuto-check passed

More from kostja94/marketing-skills

All 102 skills in this repo
  • Grokipedia Recommendations

    kostja94/marketing-skills

    When the user wants to add recommendations, links, or content to Grokipedia.

    1k GitHub starsUsed in 1 repo~4.2k tokens
    Auto-check passed
  • AI Traffic Tracking

    kostja94/marketing-skills

    When the user wants to track AI search traffic in GA4 or GSC.

    1k GitHub stars~959 tokensUpdated yesterday
    Auto-check passed
  • Analytics Tracking

    kostja94/marketing-skills

    When the user wants to set up, audit, or optimize analytics tracking (GA4, events, conversions).

    1k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Brand Visual Generator

    kostja94/marketing-skills

    When the user wants to define, audit, or apply visual identity (typography, colors, spacing, design tokens, frontend aesthetics).

    1k GitHub stars~3k tokensUpdated yesterday
    Auto-check passed
  • Canonical Tag

    kostja94/marketing-skills

    When the user wants to configure canonical URLs, fix duplicate content, or consolidate URL signals.

    1k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • Content Strategy

    kostja94/marketing-skills

    When the user wants to plan content for SEO, create content calendar, or build topic clusters.

    1k GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed

Questions about Referral Program

What does Referral Program do?

When the user wants to plan, implement, or optimize referral program strategy. Referral Program is an agent skill from kostja94/marketing-skills. When the user wants to plan, implement, or optimize referral program strategy.

When should I use Referral Program?

Referral Program fits situations like: optimize referral program strategy; the user mentions referral program; referral marketing; word-of-mouth growth.

How do I install Referral Program in Claude Code?

Run `npx skills add kostja94/marketing-skills --skill referral-program -a claude-code`. Or copy the skill folder (skills/channels/partnerships/referral-program in kostja94/marketing-skills) into .claude/skills/referral-program in your project. Claude Code loads it when a task matches its description.

How do I install Referral Program in Codex?

Run `npx skills add kostja94/marketing-skills --skill referral-program -a codex`. Or copy the skill folder (skills/channels/partnerships/referral-program in kostja94/marketing-skills) into .agents/skills/referral-program in your project. Codex loads it when a task matches its description.

Can I use Referral Program 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 kostja94/marketing-skills --skill referral-program -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, .gemini/skills/referral-program, .github/skills/referral-program and .opencode/skills/referral-program in your project.

What does Referral Program need to run?

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

Does Referral Program 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 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 use?

Referral Program 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 use?

About 1.5k tokens (SKILL.md is roughly 5.9k 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?

Skills that share tags, products or a category with Referral Program: Suede Paywalls (JasonColapietro/suede-creator-skills, 127 stars), Ad Creative Builder (aaron-he-zhu/aaron-marketing-skills, 2.9k stars), Ad Library Teardown (ScrapeCreators/social-media-research-skills, 3.3k stars) and Cro Optimization (ognjengt/founder-skills, 406 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Referral Program?

kostja94 (a GitHub user) maintains it in kostja94/marketing-skills, which has 1,016 GitHub stars. The repository holds 102 skills in this directory. The repository was last updated on October 6, 2026.

Source: kostja94/marketing-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.