Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Seek properties that emerge from combination (non-additive)
.claude/skills/yogsoth-ai-emergent-property-hunting/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-12 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 71% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 344% | 0% |
| case-23 | ✓→✗ | ▼ Worse | 162% | 0% |
| case-11 | ✓→✓ | ＝ Same ✓ | 80% | 0% |
Seek properties that emerge from combination (non-additive). Focus specifically on identifying and validating properties that exist in the combination but not in any individual component — the hallmark of genuine creative novelty.
| 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 combinations to test for emergence | | emergence-detection | Detect and validate emergent properties | | blend-construction | Construct blends to test for emergent structure |
| SOP | Role | |-----|------| | emergent-property-identification | Identify non-additive properties | | blend-elaboration | Run combinations as mental simulations | | vital-relation-mapping | Map relations that enable emergence | | combinatorial-synthesis | Synthesize emergence findings |
<!-- 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 | | --- | --- | | blend-elaboration | Run blend as mental simulation | | combinatorial-synthesis | Synthesize all combinatorial creativity outputs | | emergent-property-identification | Identify non-additive properties from combinations | | 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-03 | fail→fail | 28,458 | 48,800 | +71% | 1 | 1 | 0% | 4,075 | 6,873 | +69% | 0 | 0 | — |
case-04 | fail→fail | 24,849 | 38,269 | +54% | 1 | 1 | 0% | 4,147 | 6,844 | +65% | 0 | 0 | — |
case-11 | pass→pass | 27,908 | 40,651 | +46% | 1 | 1 | 0% | 3,787 | 6,830 | +80% | 0 | 0 | — |
case-01 | pass→pass | 26,245 | 40,993 | +56% | 1 | 1 | 0% | 3,858 | 6,834 | +77% | 0 | 0 | — |
case-02 | fail→fail | 24,217 | 44,047 | +82% | 1 | 1 | 0% | 3,430 | 6,878 | +101% | 0 | 0 | — |
case-05 | fail→fail | 21,289 | 40,411 | +90% | 1 | 1 | 0% | 3,124 | 6,539 | +109% | 0 | 0 | — |
case-06 | fail→fail | 22,205 | 41,374 | +86% | 1 | 1 | 0% | 3,087 | 6,836 | +121% | 0 | 0 | — |
case-07 | pass→pass | 22,521 | 42,789 | +90% | 1 | 1 | 0% | 3,091 | 6,841 | +121% | 0 | 0 | — |
case-08 | pass→pass | 24,943 | 41,182 | +65% | 1 | 1 | 0% | 3,585 | 6,831 | +91% | 0 | 0 | — |
case-09 | fail→fail | 21,330 | 44,909 | +111% | 1 | 1 | 0% | 2,956 | 6,836 | +131% | 0 | 0 | — |
case-10 | fail→fail | 23,571 | 31,761 | +35% | 1 | 1 | 0% | 3,306 | 5,081 | +54% | 0 | 0 | — |
case-12 | fail→pass | 20,693 | 29,288 | +42% | 1 | 1 | 0% | 2,887 | 4,813 | +67% | 0 | 0 | — |
case-13 | fail→fail | 18,383 | 40,806 | +122% | 1 | 1 | 0% | 2,513 | 6,829 | +172% | 0 | 0 | — |
case-14 | fail→fail | 20,346 | 41,951 | +106% | 1 | 1 | 0% | 2,995 | 6,823 | +128% | 0 | 0 | — |
case-15 | fail→fail | 25,063 | 42,541 | +70% | 1 | 1 | 0% | 3,720 | 6,821 | +83% | 0 | 0 | — |
case-16 | fail→pass | 25,399 | 40,427 | +59% | 1 | 1 | 0% | 3,990 | 6,821 | +71% | 0 | 0 | — |
case-17 | fail→fail | 22,813 | 40,563 | +78% | 1 | 1 | 0% | 3,307 | 6,824 | +106% | 0 | 0 | — |
case-18 | fail→fail | 21,192 | 45,932 | +117% | 1 | 1 | 0% | 3,103 | 6,823 | +120% | 0 | 0 | — |
case-19 | fail→fail | 16,238 | 42,026 | +159% | 1 | 1 | 0% | 2,397 | 6,832 | +185% | 0 | 0 | — |
case-20 | fail→fail | 20,772 | 38,313 | +84% | 1 | 1 | 0% | 3,422 | 6,821 | +99% | 0 | 0 | — |
case-21 | fail→pass | 9,655 | 32,479 | +236% | 1 | 1 | 0% | 1,379 | 6,124 | +344% | 0 | 0 | — |
case-22 | pass→pass | 16,476 | 30,799 | +87% | 1 | 1 | 0% | 2,592 | 5,764 | +122% | 0 | 0 | — |
case-23 | pass→fail | 16,843 | 39,783 | +136% | 1 | 1 | 0% | 2,612 | 6,842 | +162% | 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 +9 percentage points is the difference between those two pass rates over the 23 comparable cases. 2 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.