Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate a Lean Canvas with problem, solution, metrics, cost structure, UVP, unfair advantage, channels, segments, and revenue. Use when exploring a lean startup canvas, testing a business hypothesis, or modeling a new venture.
.claude/skills/phuryn-lean-canvas/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flashlowest | 78% | 9 |
| gemini-3.1-pro-preview | 100% | 1 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 55% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 41% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 27% | 0% |
You are a business model strategist designing a Lean Canvas for $ARGUMENTS.
Your task is to create a comprehensive Lean Canvas that outlines the business hypothesis and key business model assumptions for the product.
1. Problem
2. Solution
3. Unique Value Proposition (UVP)
4. Unfair Advantage
5. Customer Segments
6. Channels
7. Revenue Streams
8. Cost Structure
9. Key Metrics
Lean Canvas vs Business Model Canvas vs Startup Canvas:
Lean Canvas (Ash Maurya) is a startup-focused adaptation of the Business Model Canvas that replaces Partners/Activities/Resources with Problem/Solution/Unfair Advantage. It's fast and hypothesis-driven, but has known limitations:
When to use Lean Canvas: Quick hypothesis testing when you need speed over completeness. Best as a brainstorming tool, not a strategy document.
Consider instead: Startup Canvas (Paweł Huryn) separates strategy (9 sections from the Product Strategy Canvas) from business model (Cost Structure + Revenue Streams). Recommended when you need both strategic clarity AND a business model for a new product.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 32,812 | 22,173 | -32% | 1 | 1 | 0% | 4,309 | 4,702 | +9% | 0 | 0 | — |
case-02 | fail→pass | 27,120 | 24,081 | -11% | 1 | 1 | 0% | 4,025 | 4,636 | +15% | 0 | 0 | — |
case-03 | fail→pass | 19,400 | 20,072 | +3% | 1 | 1 | 0% | 3,013 | 4,313 | +43% | 0 | 0 | — |
case-04 | pass→pass | 23,878 | 24,024 | +1% | 1 | 1 | 0% | 3,088 | 4,948 | +60% | 0 | 0 | — |
case-05 | fail→pass | 22,611 | 21,889 | -3% | 1 | 1 | 0% | 3,238 | 5,003 | +55% | 0 | 0 | — |
case-06 | fail→pass | 16,825 | 18,112 | +8% | 1 | 1 | 0% | 2,893 | 4,079 | +41% | 0 | 0 | — |
case-07 | fail→pass | 20,433 | 27,008 | +32% | 1 | 1 | 0% | 3,401 | 4,334 | +27% | 0 | 0 | — |
case-08 | pass→pass | 14,100 | 22,135 | +57% | 1 | 1 | 0% | 2,444 | 4,213 | +72% | 0 | 0 | — |
case-09 | pass→pass | 24,473 | 20,289 | -17% | 1 | 1 | 0% | 3,332 | 4,465 | +34% | 0 | 0 | — |
case-10 | fail→pass | 18,393 | 28,774 | +56% | 1 | 1 | 0% | 2,715 | 5,249 | +93% | 0 | 0 | — |
case-11 | fail→pass | 16,926 | 20,031 | +18% | 1 | 1 | 0% | 2,699 | 4,475 | +66% | 0 | 0 | — |
case-12 | pass→pass | 18,172 | 19,515 | +7% | 1 | 1 | 0% | 3,141 | 4,215 | +34% | 0 | 0 | — |
case-13 | fail→fail | 24,187 | 23,555 | -3% | 1 | 1 | 0% | 3,357 | 4,885 | +46% | 0 | 0 | — |
case-14 | pass→pass | 18,278 | 23,419 | +28% | 1 | 1 | 0% | 3,041 | 3,968 | +30% | 0 | 0 | — |
case-15 | fail→pass | 18,304 | 22,192 | +21% | 1 | 1 | 0% | 3,094 | 4,632 | +50% | 0 | 0 | — |
case-16 | pass→pass | 13,185 | 24,981 | +89% | 1 | 1 | 0% | 2,399 | 4,287 | +79% | 0 | 0 | — |
case-17 | fail→pass | 15,746 | 15,351 | -3% | 1 | 1 | 0% | 2,091 | 3,580 | +71% | 0 | 0 | — |
case-18 | pass→pass | 15,036 | 20,757 | +38% | 1 | 1 | 0% | 2,546 | 4,211 | +65% | 0 | 0 | — |
case-19 | fail→pass | 13,930 | 16,687 | +20% | 1 | 1 | 0% | 2,368 | 4,281 | +81% | 0 | 0 | — |
case-20 | pass→pass | 15,127 | 22,634 | +50% | 1 | 1 | 0% | 2,735 | 4,976 | +82% | 0 | 0 | — |
case-21 | pass→pass | 26,239 | 21,490 | -18% | 1 | 1 | 0% | 3,422 | 4,581 | +34% | 0 | 0 | — |
case-22 | pass→pass | 13,894 | 17,956 | +29% | 1 | 1 | 0% | 2,405 | 3,471 | +44% | 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 +45 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.