Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Assemble 2-3 complementary experts to collaboratively analyze anything. Experts work together to explore topics from multiple expert angles.
.claude/skills/onewave-ai-expert-panel/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -42% | 0% |
Assemble 2-3 complementary experts to collaboratively analyze anything. Experts work together to explore topics from multiple expert angles.
You are a master panel moderator. Assemble 2-3 domain experts who collaboratively analyze topics. Structure: Initial analysis, cross-pollination of ideas, synthesis, and integrated recommendations. Experts build on each other's insights and create comprehensive analyses.
markdown# Expert Panel 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-02 | fail→pass | 25,602 | 18,778 | -27% | 1 | 1 | 0% | 3,691 | 2,921 | -21% | 0 | 0 | — |
case-01 | fail→pass | 21,984 | 39,815 | +81% | 1 | 1 | 0% | 3,189 | 3,318 | +4% | 0 | 0 | — |
case-03 | fail→pass | 27,799 | 19,753 | -29% | 1 | 1 | 0% | 4,132 | 3,412 | -17% | 0 | 0 | — |
case-04 | fail→fail | 14,743 | 15,132 | +3% | 1 | 1 | 0% | 2,012 | 2,277 | +13% | 0 | 0 | — |
case-05 | fail→pass | 36,636 | 24,088 | -34% | 1 | 1 | 0% | 5,068 | 3,970 | -22% | 0 | 0 | — |
case-06 | fail→fail | 7,176 | 14,308 | +99% | 1 | 1 | 0% | 1,057 | 2,473 | +134% | 0 | 0 | — |
case-07 | fail→fail | 26,089 | 26,093 | +0% | 1 | 1 | 0% | 3,285 | 4,222 | +29% | 0 | 0 | — |
case-08 | fail→fail | 27,870 | 19,115 | -31% | 1 | 1 | 0% | 3,595 | 3,011 | -16% | 0 | 0 | — |
case-09 | fail→fail | 19,409 | 24,336 | +25% | 1 | 1 | 0% | 2,644 | 3,743 | +42% | 0 | 0 | — |
case-10 | fail→pass | 46,752 | 22,914 | -51% | 1 | 1 | 0% | 6,173 | 3,572 | -42% | 0 | 0 | — |
case-11 | fail→fail | 12,444 | 15,951 | +28% | 1 | 1 | 0% | 1,829 | 2,726 | +49% | 0 | 0 | — |
case-12 | fail→pass | 31,301 | 34,868 | +11% | 1 | 1 | 0% | 4,834 | 5,647 | +17% | 0 | 0 | — |
case-13 | fail→pass | 26,202 | 17,407 | -34% | 1 | 1 | 0% | 4,106 | 3,037 | -26% | 0 | 0 | — |
case-14 | fail→fail | 33,383 | 22,319 | -33% | 1 | 1 | 0% | 4,746 | 3,761 | -21% | 0 | 0 | — |
case-15 | fail→pass | 12,396 | 18,727 | +51% | 1 | 1 | 0% | 1,683 | 3,107 | +85% | 0 | 0 | — |
case-16 | fail→pass | 10,832 | 23,322 | +115% | 1 | 1 | 0% | 1,616 | 3,973 | +146% | 0 | 0 | — |
case-17 | fail→pass | 12,704 | 13,212 | +4% | 1 | 1 | 0% | 2,444 | 2,746 | +12% | 0 | 0 | — |
case-18 | fail→fail | 20,998 | 26,422 | +26% | 1 | 1 | 0% | 3,091 | 4,441 | +44% | 0 | 0 | — |
case-19 | fail→fail | 12,477 | 13,897 | +11% | 1 | 1 | 0% | 2,269 | 2,331 | +3% | 0 | 0 | — |
case-20 | pass→pass | 5,327 | 6,227 | +17% | 1 | 1 | 0% | 1,158 | 1,591 | +37% | 0 | 0 | — |
case-21 | pass→pass | 6,496 | 10,256 | +58% | 1 | 1 | 0% | 1,169 | 2,260 | +93% | 0 | 0 | — |
case-22 | pass→pass | 4,286 | 5,859 | +37% | 1 | 1 | 0% | 870 | 1,476 | +70% | 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.