Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →This skill should be used when the user asks to "calculate TAM", "determine SAM", "estimate SOM", "size the market", "calculate market opportunity", "what's the total addressable market", or requests market sizing analysis for a startup or business opportunity.
.claude/skills/dokhacgiakhoa-market-sizing-analysis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 24% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 45% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 43% | 0% |
| case-07 | ✓→✓ | ＝ Same ✓ | 40% | 0% |
Comprehensive market sizing methodologies for calculating Total Addressable Market (TAM), Serviceable Available Market (SAM), and Serviceable Obtainable Market (SOM) for startup opportunities.
resources/implementation-playbook.md.Market sizing provides the foundation for startup strategy, fundraising, and business planning. Calculate market opportunity using three complementary methodologies: top-down (industry reports), bottom-up (customer segment calculations), and value theory (willingness to pay).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 20,236 | 28,183 | +39% | 1 | 1 | 0% | 3,926 | 5,425 | +38% | 0 | 0 | — |
case-02 | fail→fail | 40,086 | 25,718 | -36% | 1 | 1 | 0% | 8,238 | 5,860 | -29% | 0 | 0 | — |
case-03 | fail→fail | 36,722 | 24,102 | -34% | 1 | 1 | 0% | 6,624 | 5,284 | -20% | 0 | 0 | — |
case-04 | pass→pass | 16,909 | 17,181 | +2% | 1 | 1 | 0% | 3,033 | 3,772 | +24% | 0 | 0 | — |
case-05 | pass→pass | 14,083 | 15,631 | +11% | 1 | 1 | 0% | 2,357 | 3,417 | +45% | 0 | 0 | — |
case-06 | pass→pass | 12,298 | 15,658 | +27% | 1 | 1 | 0% | 2,022 | 2,887 | +43% | 0 | 0 | — |
case-07 | pass→pass | 11,646 | 10,195 | -12% | 1 | 1 | 0% | 1,991 | 2,794 | +40% | 0 | 0 | — |
case-08 | fail→pass | 25,586 | 20,676 | -19% | 1 | 1 | 0% | 2,893 | 3,688 | +27% | 0 | 0 | — |
case-09 | pass→pass | 14,549 | 13,564 | -7% | 1 | 1 | 0% | 2,255 | 2,831 | +26% | 0 | 0 | — |
case-10 | pass→pass | 13,296 | 11,501 | -14% | 1 | 1 | 0% | 2,053 | 2,413 | +18% | 0 | 0 | — |
case-11 | pass→pass | 11,133 | 10,585 | -5% | 1 | 1 | 0% | 1,830 | 2,634 | +44% | 0 | 0 | — |
case-12 | fail→fail | 23,885 | 17,464 | -27% | 1 | 1 | 0% | 3,162 | 3,513 | +11% | 0 | 0 | — |
case-13 | pass→pass | 22,790 | 20,613 | -10% | 1 | 1 | 0% | 3,426 | 4,270 | +25% | 0 | 0 | — |
case-14 | pass→pass | 11,997 | 16,266 | +36% | 1 | 1 | 0% | 2,127 | 3,182 | +50% | 0 | 0 | — |
case-15 | pass→pass | 13,248 | 18,719 | +41% | 1 | 1 | 0% | 2,190 | 3,638 | +66% | 0 | 0 | — |
case-16 | pass→pass | 16,300 | 17,903 | +10% | 1 | 1 | 0% | 2,254 | 3,156 | +40% | 0 | 0 | — |
case-17 | pass→pass | 12,310 | 9,610 | -22% | 1 | 1 | 0% | 1,960 | 2,536 | +29% | 0 | 0 | — |
case-18 | pass→pass | 11,413 | 13,657 | +20% | 1 | 1 | 0% | 1,838 | 2,970 | +62% | 0 | 0 | — |
case-19 | pass→pass | 15,834 | 20,163 | +27% | 1 | 1 | 0% | 2,283 | 3,560 | +56% | 0 | 0 | — |
case-20 | pass→pass | 15,205 | 10,883 | -28% | 1 | 1 | 0% | 2,281 | 2,494 | +9% | 0 | 0 | — |
case-21 | fail→fail | 31,555 | 31,348 | -1% | 1 | 1 | 0% | 7,225 | 7,356 | +2% | 0 | 0 | — |
case-22 | fail→fail | 18,243 | 18,999 | +4% | 1 | 1 | 0% | 3,374 | 3,667 | +9% | 0 | 0 | — |
case-23 | fail→fail | 25,067 | 21,149 | -16% | 1 | 1 | 0% | 3,896 | 4,651 | +19% | 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 +4 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.