Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Simultaneous concept collision at multiple abstraction levels
.claude/skills/yogsoth-ai-multi-level-bisociation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 64% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 117% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 71% | 0% |
Simultaneous concept collision at multiple abstraction levels. Unlike single-level bisociation, this strategy forces collision at concrete, functional, structural, and abstract levels simultaneously, producing richer creative output.
| Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 25 | 0 | 0% | | web-research | 10 | 0 | 0% | | paper-overview | 25 | 0 | 0% | | paper-search | 15 | 0 | 0% | | paper-research | 8 | 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 collision points across levels | | blend-construction | Construct blends at each abstraction level | | emergence-detection | Detect cross-level emergent properties |
| SOP | Role | |-----|------| | abstraction-ladder | Decompose concepts into multiple abstraction levels | | vital-relation-mapping | Map vital relations at each level | | blend-composition | Compose collisions into novel connections | | emergent-property-identification | Identify non-additive properties from multi-level collision | | combinatorial-synthesis | Synthesize multi-level bisociation outputs |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | blend-construction | Construct complete 4-space blends with emergent structure. Orchestrates input-space-construction → generic-space-extraction → blend-composition. | | emergence-detection | Detect and validate emergent properties from combinations. Orchestrates emergent-property-identification → blend-elaboration. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | abstraction-ladder | Perform bisociation at multiple abstraction levels | | blend-composition | Compose new connections in blended space | | combinatorial-synthesis | Synthesize all combinatorial creativity outputs | | generic-space-extraction | Extract shared abstract structure from two input spaces | | vital-relation-mapping | Map 15 vital relations between 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 | fail→fail | 53,320 | 22,789 | -57% | 1 | 1 | 0% | 8,256 | 1,506 | -82% | 0 | 0 | — |
case-02 | pass→pass | 41,025 | 64,029 | +56% | 1 | 1 | 0% | 6,084 | 7,976 | +31% | 0 | 0 | — |
case-03 | fail→pass | 53,258 | 57,041 | +7% | 1 | 1 | 0% | 7,481 | 8,933 | +19% | 0 | 0 | — |
case-04 | fail→pass | 58,946 | 55,406 | -6% | 1 | 1 | 0% | 7,292 | 8,908 | +22% | 0 | 0 | — |
case-05 | fail→pass | 54,729 | 41,150 | -25% | 1 | 1 | 0% | 4,617 | 7,551 | +64% | 0 | 0 | — |
case-06 | fail→pass | 23,057 | 65,748 | +185% | 1 | 1 | 0% | 4,093 | 8,901 | +117% | 0 | 0 | — |
case-07 | pass→pass | 64,954 | 48,850 | -25% | 1 | 1 | 0% | 4,302 | 7,629 | +77% | 0 | 0 | — |
case-08 | pass→pass | 55,276 | 154,502 | +180% | 1 | 1 | 0% | 3,858 | 8,902 | +131% | 0 | 0 | — |
case-09 | pass→pass | 34,501 | 42,476 | +23% | 1 | 1 | 0% | 3,880 | 6,891 | +78% | 0 | 0 | — |
case-10 | pass→pass | 46,133 | 52,700 | +14% | 1 | 1 | 0% | 7,448 | 8,896 | +19% | 0 | 0 | — |
case-17 | fail→fail | 10,117 | 16,517 | +63% | 1 | 1 | 0% | 1,592 | 3,053 | +92% | 0 | 0 | — |
case-11 | fail→fail | 42,624 | 9,278 | -78% | 1 | 1 | 0% | 6,925 | 1,262 | -82% | 0 | 0 | — |
case-12 | pass→pass | 31,446 | 63,380 | +102% | 1 | 1 | 0% | 3,905 | 8,867 | +127% | 0 | 0 | — |
case-13 | pass→pass | 18,907 | 35,235 | +86% | 1 | 1 | 0% | 3,527 | 6,319 | +79% | 0 | 0 | — |
case-14 | pass→fail | 35,086 | 46,255 | +32% | 1 | 1 | 0% | 8,228 | 8,773 | +7% | 0 | 0 | — |
case-15 | fail→pass | 37,743 | 59,724 | +58% | 1 | 1 | 0% | 5,213 | 8,904 | +71% | 0 | 0 | — |
case-16 | pass→pass | 48,006 | 78,516 | +64% | 1 | 1 | 0% | 8,158 | 8,904 | +9% | 0 | 0 | — |
case-18 | pass→pass | 38,083 | 53,197 | +40% | 1 | 1 | 0% | 5,827 | 8,902 | +53% | 0 | 0 | — |
case-19 | fail→fail | 28,626 | 47,466 | +66% | 1 | 1 | 0% | 4,351 | 6,738 | +55% | 0 | 0 | — |
case-20 | pass→fail | 36,725 | 61,749 | +68% | 1 | 1 | 0% | 5,531 | 1,353 | -76% | 0 | 0 | — |
case-21 | pass→pass | 28,041 | 51,455 | +83% | 1 | 1 | 0% | 4,415 | 8,905 | +102% | 0 | 0 | — |
case-22 | fail→fail | 45,427 | 10,799 | -76% | 1 | 1 | 0% | 7,827 | 1,437 | -82% | 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 18 counted toward the lift figure. The other 4 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 +14 percentage points is the difference between those two pass rates over the 18 comparable cases. 3 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.