Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Identify growth loops (flywheels) for sustainable traction. Evaluates 5 loop types: Viral, Usage, Collaboration, User-Generated, and Referral. Use when designing growth mechanisms, building product-led traction, or understanding how growth loops work.
.claude/skills/phuryn-growth-loops/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -23% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 42% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 68% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 39% | 0% |
Identify and design growth loops (flywheels) that create sustainable traction. This skill evaluates five proven growth loop mechanisms to reduce reliance on paid acquisition and build product-led growth.
Product content created by users gets shared on external platforms, bringing new users back to the product.
Users create content or value within the product, then share it, which invites new users or drives re-engagement.
Users invite colleagues to co-create or collaborate within the product, expanding the user base within organizations.
Users discover new content or features through other users' creations, then create and share their own content.
Users invite other potential users in exchange for rewards, incentives, or social recognition.
Clarify the core value users experience:
Assess which growth loops align with your product:
Create specific loop implementation:
Estimate growth velocity:
Implement the highest-leverage loop first:
Use $ARGUMENTS to pass:
A growth loops analysis including:
Based on growth loops research by Ognjen Bošković. Focuses on compounding user acquisition through built-in, product-native sharing and collaboration mechanisms.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 37,992 | 59,203 | +56% | 1 | 1 | 0% | 6,260 | 5,799 | -7% | 0 | 0 | — |
case-02 | fail→fail | 59,457 | 23,424 | -61% | 1 | 1 | 0% | 4,970 | 4,976 | +0% | 0 | 0 | — |
case-03 | fail→pass | 35,666 | 21,162 | -41% | 1 | 1 | 0% | 6,243 | 4,828 | -23% | 0 | 0 | — |
case-04 | pass→pass | 15,971 | 16,588 | +4% | 1 | 1 | 0% | 2,774 | 3,785 | +36% | 0 | 0 | — |
case-05 | pass→pass | 21,619 | 20,464 | -5% | 1 | 1 | 0% | 3,344 | 5,009 | +50% | 0 | 0 | — |
case-06 | pass→pass | 17,246 | 14,934 | -13% | 1 | 1 | 0% | 2,335 | 4,011 | +72% | 0 | 0 | — |
case-07 | fail→pass | 29,878 | 23,335 | -22% | 1 | 1 | 0% | 3,760 | 5,323 | +42% | 0 | 0 | — |
case-08 | fail→pass | 17,958 | 21,963 | +22% | 1 | 1 | 0% | 2,880 | 4,825 | +68% | 0 | 0 | — |
case-09 | fail→pass | 19,707 | 21,275 | +8% | 1 | 1 | 0% | 3,337 | 4,626 | +39% | 0 | 0 | — |
case-10 | fail→fail | 17,503 | 14,634 | -16% | 1 | 1 | 0% | 2,613 | 3,602 | +38% | 0 | 0 | — |
case-11 | fail→pass | 16,979 | 19,849 | +17% | 1 | 1 | 0% | 2,911 | 3,921 | +35% | 0 | 0 | — |
case-12 | fail→pass | 18,992 | 23,180 | +22% | 1 | 1 | 0% | 2,995 | 4,986 | +66% | 0 | 0 | — |
case-13 | fail→fail | 17,503 | 18,959 | +8% | 1 | 1 | 0% | 2,805 | 4,394 | +57% | 0 | 0 | — |
case-14 | pass→pass | 26,854 | 20,022 | -25% | 1 | 1 | 0% | 3,247 | 4,497 | +38% | 0 | 0 | — |
case-15 | fail→pass | 15,104 | 19,117 | +27% | 1 | 1 | 0% | 2,419 | 4,305 | +78% | 0 | 0 | — |
case-16 | fail→fail | 15,682 | 24,313 | +55% | 1 | 1 | 0% | 2,636 | 5,283 | +100% | 0 | 0 | — |
case-17 | fail→pass | 19,067 | 18,789 | -1% | 1 | 1 | 0% | 2,715 | 4,480 | +65% | 0 | 0 | — |
case-18 | fail→pass | 19,549 | 16,639 | -15% | 1 | 1 | 0% | 3,107 | 4,017 | +29% | 0 | 0 | — |
case-19 | fail→pass | 16,887 | 17,231 | +2% | 1 | 1 | 0% | 2,719 | 3,953 | +45% | 0 | 0 | — |
case-20 | pass→pass | 13,707 | 18,960 | +38% | 1 | 1 | 0% | 2,198 | 4,237 | +93% | 0 | 0 | — |
case-21 | fail→pass | 15,721 | 17,605 | +12% | 1 | 1 | 0% | 2,480 | 4,116 | +66% | 0 | 0 | — |
case-22 | fail→pass | 17,218 | 16,244 | -6% | 1 | 1 | 0% | 2,749 | 3,835 | +40% | 0 | 0 | — |
case-23 | fail→pass | 17,395 | 25,337 | +46% | 1 | 1 | 0% | 2,795 | 4,579 | +64% | 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. 23 cases were attempted. The headline lift of +61 percentage points is the difference between those two pass rates over the 23 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.