Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate sports trivia questions by sport/era/difficulty. Multiple formats with obscure stats, fun facts, pub quiz ready content.
.claude/skills/onewave-ai-sports-trivia-builder/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 127% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 95% | 0% |
Generate sports trivia questions by sport/era/difficulty. Multiple formats with obscure stats, fun facts, pub quiz ready content.
You are an expert sports historian and trivia creator. Generate engaging trivia questions across sports, eras, and difficulty levels. Include: multiple choice, true/false, fill-in-blank formats, obscure stats, fun facts, answer explanations with context, and difficulty ratings.
markdown# Sports Trivia Builder Output **Generated**: {timestamp} --- ## Results [Your formatted output here] --- ## Recommendations [Actionable next steps]
Trigger Phrases:
Example Request: > "Sample user request here]"
Response Approach:
Remember: Focus on delivering value quickly and clearly!
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 22,879 | 54,304 | +137% | 1 | 1 | 0% | 3,894 | 4,956 | +27% | 0 | 0 | — |
case-02 | fail→pass | 22,177 | 22,664 | +2% | 1 | 1 | 0% | 3,881 | 4,167 | +7% | 0 | 0 | — |
case-03 | fail→pass | 36,615 | 40,065 | +9% | 1 | 1 | 0% | 6,816 | 6,536 | -4% | 0 | 0 | — |
case-04 | pass→fail | 12,033 | 17,722 | +47% | 1 | 1 | 0% | 2,032 | 3,250 | +60% | 0 | 0 | — |
case-05 | pass→pass | 19,882 | 21,835 | +10% | 1 | 1 | 0% | 3,364 | 4,169 | +24% | 0 | 0 | — |
case-06 | pass→pass | 18,358 | 15,426 | -16% | 1 | 1 | 0% | 2,842 | 2,675 | -6% | 0 | 0 | — |
case-07 | fail→pass | 5,771 | 11,910 | +106% | 1 | 1 | 0% | 1,025 | 2,326 | +127% | 0 | 0 | — |
case-08 | fail→pass | 7,984 | 15,137 | +90% | 1 | 1 | 0% | 1,219 | 2,373 | +95% | 0 | 0 | — |
case-09 | fail→pass | 8,899 | 16,442 | +85% | 1 | 1 | 0% | 1,793 | 2,763 | +54% | 0 | 0 | — |
case-10 | fail→pass | 37,889 | 30,191 | -20% | 1 | 1 | 0% | 7,568 | 5,761 | -24% | 0 | 0 | — |
case-11 | fail→pass | 16,035 | 28,076 | +75% | 1 | 1 | 0% | 2,494 | 4,653 | +87% | 0 | 0 | — |
case-12 | fail→fail | 16,317 | 25,998 | +59% | 1 | 1 | 0% | 3,156 | 4,472 | +42% | 0 | 0 | — |
case-13 | fail→pass | 6,919 | 11,035 | +59% | 1 | 1 | 0% | 1,307 | 2,408 | +84% | 0 | 0 | — |
case-14 | fail→pass | 15,505 | 16,337 | +5% | 1 | 1 | 0% | 2,807 | 3,312 | +18% | 0 | 0 | — |
case-15 | fail→pass | 16,268 | 21,622 | +33% | 1 | 1 | 0% | 2,595 | 3,552 | +37% | 0 | 0 | — |
case-16 | fail→pass | 17,330 | 21,109 | +22% | 1 | 1 | 0% | 3,256 | 3,981 | +22% | 0 | 0 | — |
case-17 | fail→pass | 31,230 | 32,457 | +4% | 1 | 1 | 0% | 4,984 | 5,802 | +16% | 0 | 0 | — |
case-18 | fail→pass | 9,499 | 21,837 | +130% | 1 | 1 | 0% | 1,787 | 4,471 | +150% | 0 | 0 | — |
case-19 | fail→pass | 10,482 | 19,927 | +90% | 1 | 1 | 0% | 1,991 | 3,199 | +61% | 0 | 0 | — |
case-20 | fail→pass | 11,346 | 20,494 | +81% | 1 | 1 | 0% | 2,142 | 3,594 | +68% | 0 | 0 | — |
case-21 | fail→pass | 15,187 | 22,010 | +45% | 1 | 1 | 0% | 2,958 | 4,422 | +49% | 0 | 0 | — |
case-22 | fail→pass | 16,848 | 22,544 | +34% | 1 | 1 | 0% | 2,626 | 4,255 | +62% | 0 | 0 | — |
case-23 | fail→pass | 18,225 | 22,713 | +25% | 1 | 1 | 0% | 3,061 | 4,372 | +43% | 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 +78 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is 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.