Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →TAM/SAM/SOM calculator with deep market research. Produces comprehensive market-sizing.md with top-down and bottom-up estimates, methodology, data sources, assumptions, sensitivity ranges, growth projections, competitive landscape, and Mermaid visualizations. Use when user needs market size estimates, addressable market analysis, go-to-market sizing, investor-ready market analysis, or business plan market validation.
.claude/skills/onewave-ai-market-sizing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 103% | 0% |
| case-04 | ✓→✗ | ▼ Worse | -29% | 0% |
| case-05 | ✓→✗ | ▼ Worse | -63% | 0% |
| case-06 | ✓→✗ | ▼ Worse | -10% | 0% |
| case-17 | ✓→✗ | ▼ Worse | -30% | 0% |
Produce rigorous, investor-grade TAM/SAM/SOM analyses by combining top-down macro data with bottom-up unit economics, triangulating the two, and always showing the work, citing sources, flagging assumptions, and providing sensitivity ranges.
references/research-sources.md — source categories and search queries for every research lane.references/methodology.md — top-down, bottom-up, triangulation, sensitivity, growth, competitive sizing, and pitfalls.references/output-template.md — the full market-sizing.md document template, Mermaid charts, and quality checklist.Confirm these four inputs before proceeding. If any is missing or ambiguous, ask first.
| Parameter | Description | Example | |---|---|---| | Industry | The broad industry or sector | "Enterprise SaaS", "Electric Vehicles" | | Product/Service | The specific offering being sized | "AI-powered code review tool" | | Geography | Target market geography | "United States", "Global", "DACH region" | | Target Segment | The specific customer segment | "Mid-market companies (100-1000 employees)" |
references/research-sources.md. Log every source URL and date as you go.references/methodology.md.references/methodology.md.market-sizing.md using the structure in references/output-template.md. Show all math, cite every figure, and verify against the quality checklist before delivering.references/methodology.md.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 34,035 | 69,842 | +105% | 1 | 1 | 0% | 6,263 | 6,935 | +11% | 0 | 0 | — |
case-02 | fail→fail | 35,441 | 35,250 | -1% | 1 | 1 | 0% | 6,255 | 6,928 | +11% | 0 | 0 | — |
case-03 | fail→fail | 34,337 | 34,522 | +1% | 1 | 1 | 0% | 6,242 | 6,915 | +11% | 0 | 0 | — |
case-04 | pass→fail | 15,452 | 6,569 | -57% | 1 | 1 | 0% | 2,719 | 1,942 | -29% | 0 | 0 | — |
case-05 | pass→fail | 26,833 | 8,665 | -68% | 1 | 1 | 0% | 6,196 | 2,265 | -63% | 0 | 0 | — |
case-06 | pass→fail | 14,231 | 8,099 | -43% | 1 | 1 | 0% | 2,104 | 1,902 | -10% | 0 | 0 | — |
case-07 | fail→fail | 11,304 | 35,871 | +217% | 1 | 1 | 0% | 1,843 | 6,838 | +271% | 0 | 0 | — |
case-08 | pass→pass | 12,905 | 29,933 | +132% | 1 | 1 | 0% | 2,330 | 5,873 | +152% | 0 | 0 | — |
case-09 | fail→pass | 20,373 | 33,734 | +66% | 1 | 1 | 0% | 3,373 | 6,843 | +103% | 0 | 0 | — |
case-10 | fail→fail | 12,473 | 31,934 | +156% | 1 | 1 | 0% | 2,585 | 6,860 | +165% | 0 | 0 | — |
case-11 | pass→pass | 17,346 | 19,967 | +15% | 1 | 1 | 0% | 3,255 | 5,161 | +59% | 0 | 0 | — |
case-12 | pass→pass | 8,045 | 23,320 | +190% | 1 | 1 | 0% | 1,308 | 5,545 | +324% | 0 | 0 | — |
case-13 | fail→fail | 17,333 | 30,706 | +77% | 1 | 1 | 0% | 3,103 | 6,836 | +120% | 0 | 0 | — |
case-14 | pass→pass | 12,268 | 30,826 | +151% | 1 | 1 | 0% | 2,092 | 6,861 | +228% | 0 | 0 | — |
case-15 | pass→pass | 16,788 | 39,627 | +136% | 1 | 1 | 0% | 3,143 | 6,843 | +118% | 0 | 0 | — |
case-16 | pass→pass | 14,277 | 18,142 | +27% | 1 | 1 | 0% | 2,770 | 4,193 | +51% | 0 | 0 | — |
case-22 | fail→fail | 16,609 | 4,838 | -71% | 1 | 1 | 0% | 2,733 | 1,535 | -44% | 0 | 0 | — |
case-17 | pass→fail | 17,708 | 7,118 | -60% | 1 | 1 | 0% | 2,709 | 1,902 | -30% | 0 | 0 | — |
case-18 | fail→fail | 21,991 | 7,128 | -68% | 1 | 1 | 0% | 3,439 | 1,950 | -43% | 0 | 0 | — |
case-19 | pass→fail | 24,287 | 8,395 | -65% | 1 | 1 | 0% | 3,928 | 1,933 | -51% | 0 | 0 | — |
case-20 | pass→pass | 14,479 | 12,738 | -12% | 1 | 1 | 0% | 2,298 | 2,884 | +26% | 0 | 0 | — |
case-21 | pass→pass | 14,334 | 19,161 | +34% | 1 | 1 | 0% | 2,403 | 4,214 | +75% | 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 -50 percentage points is the difference between those two pass rates over the 22 comparable cases. 6 cases got worse with the skill loaded, and they are included in that figure.
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.