Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Parametric variation + constraint satisfaction combinatorial search
.claude/skills/yogsoth-ai-design-space-exploration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -32% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 19% | 0% |
Parametric variation + constraint satisfaction combinatorial search. Systematically explore the combinatorial design space by varying parameters under constraints to find novel viable configurations.
| Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 20 | 0 | 0% | | web-research | 8 | 0 | 0% | | paper-overview | 20 | 0 | 0% | | paper-search | 12 | 0 | 0% | | paper-research | 5 | 0 | 0% |
Cannot exit strategy until ≥80% of each budget line is consumed OR yield targets are met with justification for remaining budget.
| Tactic | Role | |--------|------| | combination-mapping | Enumerate parameter dimensions and generate viable combinations | | emergence-detection | Detect emergent properties in novel configurations |
| SOP | Role | |-----|------| | input-space-construction | Build parameter spaces for design dimensions | | generic-space-extraction | Extract shared constraints across configurations | | emergent-property-identification | Identify non-additive properties in novel configurations | | combinatorial-synthesis | Synthesize design space exploration outputs |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | combinatorial-synthesis | Synthesize all combinatorial creativity outputs | | emergent-property-identification | Identify non-additive properties from combinations | | input-space-construction | Build input spaces for two source concepts |
<!-- END available-tables (generated) -->
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 10,577 | 4,660 | -56% | 1 | 1 | 0% | 1,532 | 1,297 | -15% | 0 | 0 | — |
case-02 | pass→pass | 7,161 | 4,246 | -41% | 1 | 1 | 0% | 1,095 | 1,234 | +13% | 0 | 0 | — |
case-03 | fail→pass | 11,282 | 2,600 | -77% | 1 | 1 | 0% | 1,698 | 905 | -47% | 0 | 0 | — |
case-04 | fail→pass | 10,265 | 3,937 | -62% | 1 | 1 | 0% | 1,532 | 1,064 | -31% | 0 | 0 | — |
case-05 | pass→pass | 8,653 | 1,968 | -77% | 1 | 1 | 0% | 1,304 | 802 | -38% | 0 | 0 | — |
case-10 | pass→pass | 9,156 | 1,896 | -79% | 1 | 1 | 0% | 1,424 | 770 | -46% | 0 | 0 | — |
case-06 | fail→pass | 9,676 | 3,343 | -65% | 1 | 1 | 0% | 1,443 | 976 | -32% | 0 | 0 | — |
case-07 | pass→pass | 9,005 | 2,589 | -71% | 1 | 1 | 0% | 1,430 | 909 | -36% | 0 | 0 | — |
case-08 | fail→pass | 10,377 | 2,424 | -77% | 1 | 1 | 0% | 1,501 | 863 | -43% | 0 | 0 | — |
case-09 | pass→pass | 6,849 | 7,608 | +11% | 1 | 1 | 0% | 1,068 | 1,195 | +12% | 0 | 0 | — |
case-11 | pass→pass | 8,286 | 1,863 | -78% | 1 | 1 | 0% | 1,290 | 754 | -42% | 0 | 0 | — |
case-12 | pass→pass | 6,935 | 2,428 | -65% | 1 | 1 | 0% | 1,060 | 884 | -17% | 0 | 0 | — |
case-13 | pass→pass | 9,383 | 4,374 | -53% | 1 | 1 | 0% | 1,372 | 1,121 | -18% | 0 | 0 | — |
case-14 | fail→pass | 8,508 | 6,734 | -21% | 1 | 1 | 0% | 1,250 | 1,490 | +19% | 0 | 0 | — |
case-15 | fail→pass | 8,630 | 2,136 | -75% | 1 | 1 | 0% | 1,218 | 823 | -32% | 0 | 0 | — |
case-16 | fail→pass | 23,933 | 2,222 | -91% | 1 | 1 | 0% | 1,325 | 803 | -39% | 0 | 0 | — |
case-17 | fail→pass | 30,145 | 1,521 | -95% | 1 | 1 | 0% | 2,307 | 708 | -69% | 0 | 0 | — |
case-18 | fail→pass | 6,619 | 1,612 | -76% | 1 | 1 | 0% | 888 | 742 | -16% | 0 | 0 | — |
case-19 | fail→pass | 6,604 | 1,576 | -76% | 1 | 1 | 0% | 980 | 713 | -27% | 0 | 0 | — |
case-20 | pass→pass | 7,503 | 7,362 | -2% | 1 | 1 | 0% | 1,660 | 2,036 | +23% | 0 | 0 | — |
case-21 | pass→fail | 13,599 | 25,016 | +84% | 1 | 1 | 0% | 2,659 | 5,594 | +110% | 0 | 0 | — |
case-22 | pass→pass | 17,862 | 37,661 | +111% | 1 | 1 | 0% | 2,995 | 5,881 | +96% | 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, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +41 percentage points is the difference between those two pass rates over the 21 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.