- name
SKILL.md
스킬 파일은 게시자의 저장소에 그대로 있습니다.
복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add borghei/Claude-Skills --skill referral-program -a cursor -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add borghei/Claude-Skills --skill referral-program -a claude-code -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add borghei/Claude-Skills --skill referral-program -a codex -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add borghei/Claude-Skills --skill referral-program -a grok -y복사한 메시지를 Grok Bot 채팅에 보냅니다. Bot이 GitHub에서 이 SKILL.md를 가져와 모든 Bot이 공유하는 스킬에 추가합니다.
Install this skill: https://github.com/borghei/Claude-Skills/tree/HEAD/business-growth/referral-program게시자 제공
Production-grade referral and affiliate program framework covering the 4-stage referral loop, incentive design methodology, trigger moment optimization, share mechanics, viral coefficient modeling, affiliate program architecture, and systematic optimization playbook. Designed to build programs that compound, not collect dust.
Before designing the referral program, settle the inputs below. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.
Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top.
referral_economics_calculator.py, referral_funnel_analyzer.py, affiliate_commission_modeler.py) to size rewards, find the weakest stage, and model affiliate tiers.Load the reference that matches the task — keep this file lean and pull detail on demand:
In scope: Customer referral program design (4-stage loop), incentive structure (single-sided, double-sided, tiered), trigger moment architecture, share mechanics, referral landing page specifications, viral coefficient modeling, affiliate program framework (commission models, tier systems, recruitment), and systematic optimization playbook.
Out of scope: Referral landing page visual design and CRO (use page-cro), signup flow optimization for referred users (use signup-flow-cro), post-signup onboarding for referred users (use onboarding-cro), churn prevention for referred customers (use churn-prevention), and reward pricing alignment (use pricing-strategy). Scripts operate on local data only -- no integrations with referral platforms (ReferralHero, Viral Loops, PartnerStack, etc.).
Limitations: K-factor benchmarks assume consumer or prosumer SaaS; B2B enterprise referral programs have different dynamics (lower K but higher per-referral value). Affiliate commission benchmarks (20-30% recurring) are SaaS-specific; marketplace and e-commerce commissions follow different models. Attribution windows (30-90 day cookies) face increasing limitations from browser privacy features (Safari ITP, Chrome third-party cookie deprecation). Revenue projections are estimates based on provided conversion rates.
>
---name: referral-programdescription: >---# business-growth/referral-program/SKILL.mdFAQ
게시자에게서 business-growth/referral-program/SKILL.md를 다운로드하거나 경로를 복사해 저장소를 엽니다. PlugMCP는 스킬을 목록에 올릴 뿐 파일을 호스팅하지 않습니다.
게시자가 https://github.com/borghei/Claude-Skills에서 관리합니다.
Claude, Cursor, Codex, Grok Build는 게시자의 저장소에서 추가한 SKILL.md를 읽을 수 있습니다. Grok Bot은 채팅에서 스킬의 GitHub 폴더 링크를 보내면 설치합니다.