Install any skill in seconds. Free to start, no credit card required.
Get Started Free →紹介プログラム・アフィリエイト・口コミ戦略を設計・最適化するスキル。 「紹介プログラムを作りたい」「アフィリエイト設計」「口コミ施策を考えて」等のリクエストで発動。
.claude/skills/minicoohei-referral-program/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 46% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 56% | 0% |
| case-06 | ✓→✓ | = Same ✓ | 21% | 0% |
You are an expert in viral growth and referral marketing. Your goal is to help design and optimize programs that turn customers into growth engines.
Check for product marketing context first: If .claude/product-marketing-context.md exists, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Gather this context (ask if not provided):
Best for:
Characteristics:
Best for:
Characteristics:
Trigger Moment → Share Action → Convert Referred → Reward → (Loop)High-intent moments:
Ranked by effectiveness:
Single-sided rewards (referrer only): Simpler, works for high-value products
Double-sided rewards (both parties): Higher conversion, win-win framing
Tiered rewards: Gamifies referral process, increases engagement
For examples and incentive sizing: See references/program-examples.md
If few customers are referring:
If referrals aren't converting:
Incentive tests: Amount, type, single vs. double-sided, timing
Messaging tests: Program description, CTA copy, landing page copy
Placement tests: Where and when the referral prompt appears
| Problem | Fix | |---------|-----| | Low awareness | Add prominent in-app prompts | | Low share rate | Simplify to one click | | Low conversion | Optimize referred user experience | | Fraud/abuse | Add verification, limits | | One-time referrers | Add tiered/gamified rewards |
Program health:
Business impact:
Subject: You can now earn [reward] for sharing [Product]
We just launched our referral program!
Share [Product] with friends and earn [reward] for each signup.
They get [their reward] too.
[Unique referral link]
1. Share your link
2. Friend signs up
3. You both get [reward]For detailed affiliate program design, commission structures, recruitment, and tools: See references/affiliate-programs.md
For implementation, see the tools registry. Key tools for referral programs:
| Tool | Best For | Guide | |------|----------|-------| | Rewardful | Stripe-native affiliate programs | rewardful.md | | Tolt | SaaS affiliate programs | tolt.md | | Mention Me | Enterprise referral programs | mention-me.md | | Dub.co | Link tracking and attribution | dub-co.md | | Stripe | Payment processing (for commission tracking) | stripe.md |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 22,577 | 16,287 | -28% | 1 | 1 | 0% | 3,601 | 4,244 | +18% | 0 | 0 | — |
case-02 | fail→fail | 18,621 | 15,101 | -19% | 1 | 1 | 0% | 3,105 | 4,206 | +35% | 0 | 0 | — |
case-03 | fail→fail | 18,211 | 15,408 | -15% | 1 | 1 | 0% | 2,932 | 3,972 | +35% | 0 | 0 | — |
case-04 | pass→pass | 12,136 | 9,048 | -25% | 1 | 1 | 0% | 2,042 | 3,185 | +56% | 0 | 0 | — |
case-05 | fail→pass | 13,752 | 8,761 | -36% | 1 | 1 | 0% | 1,975 | 2,944 | +49% | 0 | 0 | — |
case-06 | pass→pass | 11,990 | 4,764 | -60% | 1 | 1 | 0% | 1,958 | 2,375 | +21% | 0 | 0 | — |
case-07 | pass→pass | 15,210 | 11,139 | -27% | 1 | 1 | 0% | 2,489 | 3,488 | +40% | 0 | 0 | — |
case-08 | fail→pass | 13,361 | 9,724 | -27% | 1 | 1 | 0% | 2,133 | 3,104 | +46% | 0 | 0 | — |
case-09 | pass→pass | 11,338 | 11,015 | -3% | 1 | 1 | 0% | 1,910 | 3,341 | +75% | 0 | 0 | — |
case-10 | pass→pass | 12,628 | 13,231 | +5% | 1 | 1 | 0% | 1,915 | 3,719 | +94% | 0 | 0 | — |
case-11 | fail→fail | 15,244 | 9,588 | -37% | 1 | 1 | 0% | 2,327 | 3,047 | +31% | 0 | 0 | — |
case-12 | pass→pass | 9,926 | 6,273 | -37% | 1 | 1 | 0% | 1,692 | 2,651 | +57% | 0 | 0 | — |
case-13 | pass→pass | 8,634 | 5,222 | -40% | 1 | 1 | 0% | 1,336 | 2,446 | +83% | 0 | 0 | — |
case-18 | pass→pass | 17,467 | 15,379 | -12% | 1 | 1 | 0% | 2,721 | 4,040 | +48% | 0 | 0 | — |
case-14 | pass→pass | 14,157 | 17,229 | +22% | 1 | 1 | 0% | 2,168 | 4,115 | +90% | 0 | 0 | — |
case-15 | pass→pass | 14,365 | 10,095 | -30% | 1 | 1 | 0% | 2,280 | 3,099 | +36% | 0 | 0 | — |
case-16 | pass→pass | 17,087 | 13,890 | -19% | 1 | 1 | 0% | 2,601 | 3,609 | +39% | 0 | 0 | — |
case-17 | pass→pass | 10,517 | 8,992 | -15% | 1 | 1 | 0% | 1,794 | 3,014 | +68% | 0 | 0 | — |
case-19 | pass→pass | 9,773 | 11,376 | +16% | 1 | 1 | 0% | 1,441 | 3,220 | +123% | 0 | 0 | — |
case-20 | pass→pass | 18,372 | 16,105 | -12% | 1 | 1 | 0% | 3,010 | 4,194 | +39% | 0 | 0 | — |
case-21 | pass→pass | 16,925 | 14,343 | -15% | 1 | 1 | 0% | 2,665 | 3,794 | +42% | 0 | 0 | — |
case-22 | pass→pass | 14,542 | 15,695 | +8% | 1 | 1 | 0% | 2,320 | 4,097 | +77% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +14 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.