Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Bridge two unrelated thinking matrices via Koestler bisociation. Identify independent frames of reference and force collision to produce creative insight.
.claude/skills/yogsoth-ai-facet-bisociation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 45% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 76% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 136% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 69% | 0% |
Bridge two unrelated thinking matrices via Koestler bisociation — the creative act occurs at the intersection of two self-consistent but habitually incompatible frames of reference.
| Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 30 | 0 | 0% | | web-research | 10 | 0 | 0% | | paper-overview | 25 | 0 | 0% | | paper-search | 15 | 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 | |--------|------| | analogy-extraction | Extract structural principles from each matrix | | domain-divergence | Ensure the two matrices are genuinely unrelated | | bridge-validation | Validate that the bisociation produces deep insight, not surface pun |
| SOP | Role | |-----|------| | domain-scanning | Identify candidate thinking matrices | | abstraction-extraction | Abstract the logic of each matrix | | bisociation-network-construction | Build the collision network between matrices | | analogy-quality-assessment | Assess depth of the bisociative connection | | cross-domain-synthesis | Synthesize bisociation outputs into ideas |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | bridge-validation | Validate analogy depth and transfer viability. Ensures only deep structural analogies (not surface-level similarities) proceed to transfer. | | domain-divergence | Scan and select maximally diverse source domains. Ensures creative search covers genuinely unrelated fields with high transfer potential. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | abstraction-extraction | Extract abstract principles from concrete domain cases. Strips domain-specific details to reveal transferable mechanisms. | | bisociation-network-construction | Build multi-domain bridging concept network. Creates a network of collision points between multiple thinking matrices. | | cross-domain-synthesis | Synthesize all cross-domain findings into a structured idea report. Integrates outputs from all strategies and SOPs. |
<!-- 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 | pass→fail | 17,091 | 27,599 | +61% | 1 | 1 | 0% | 2,843 | 4,777 | +68% | 0 | 0 | — |
case-01 | fail→pass | 30,870 | 37,512 | +22% | 1 | 1 | 0% | 4,784 | 6,916 | +45% | 0 | 0 | — |
case-02 | fail→fail | 31,804 | 12,790 | -60% | 1 | 1 | 0% | 4,810 | 1,837 | -62% | 0 | 0 | — |
case-04 | pass→pass | 28,104 | 35,410 | +26% | 1 | 1 | 0% | 4,217 | 6,408 | +52% | 0 | 0 | — |
case-05 | pass→pass | 24,773 | 35,341 | +43% | 1 | 1 | 0% | 4,186 | 6,869 | +64% | 0 | 0 | — |
case-06 | fail→fail | 26,623 | 36,428 | +37% | 1 | 1 | 0% | 4,492 | 6,874 | +53% | 0 | 0 | — |
case-07 | pass→pass | 27,096 | 40,807 | +51% | 1 | 1 | 0% | 4,317 | 6,870 | +59% | 0 | 0 | — |
case-08 | fail→fail | 27,701 | 38,837 | +40% | 1 | 1 | 0% | 4,133 | 6,868 | +66% | 0 | 0 | — |
case-09 | fail→fail | 25,122 | 37,855 | +51% | 1 | 1 | 0% | 3,630 | 6,869 | +89% | 0 | 0 | — |
case-10 | fail→pass | 30,681 | 42,776 | +39% | 1 | 1 | 0% | 4,922 | 6,866 | +39% | 0 | 0 | — |
case-11 | fail→fail | 19,714 | 9,175 | -53% | 1 | 1 | 0% | 2,903 | 1,108 | -62% | 0 | 0 | — |
case-12 | fail→pass | 25,092 | 42,775 | +70% | 1 | 1 | 0% | 3,906 | 6,871 | +76% | 0 | 0 | — |
case-13 | fail→pass | 18,234 | 37,837 | +108% | 1 | 1 | 0% | 2,818 | 6,646 | +136% | 0 | 0 | — |
case-14 | fail→fail | 24,627 | 42,258 | +72% | 1 | 1 | 0% | 3,568 | 6,864 | +92% | 0 | 0 | — |
case-15 | fail→pass | 23,473 | 38,026 | +62% | 1 | 1 | 0% | 4,061 | 6,866 | +69% | 0 | 0 | — |
case-16 | fail→fail | 25,730 | 47,568 | +85% | 1 | 1 | 0% | 3,938 | 7,328 | +86% | 0 | 0 | — |
case-17 | pass→pass | 26,241 | 42,628 | +62% | 1 | 1 | 0% | 4,073 | 6,867 | +69% | 0 | 0 | — |
case-18 | fail→fail | 27,877 | 42,381 | +52% | 1 | 1 | 0% | 4,237 | 6,859 | +62% | 0 | 0 | — |
case-19 | pass→fail | 22,260 | 9,470 | -57% | 1 | 1 | 0% | 3,362 | 1,292 | -62% | 0 | 0 | — |
case-20 | fail→fail | 30,287 | 90,672 | +199% | 1 | 1 | 0% | 4,472 | 6,866 | +54% | 0 | 0 | — |
case-21 | fail→pass | 26,531 | 37,741 | +42% | 1 | 1 | 0% | 4,295 | 6,867 | +60% | 0 | 0 | — |
case-22 | fail→fail | 25,999 | 8,953 | -66% | 1 | 1 | 0% | 3,805 | 1,237 | -67% | 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 17 counted toward the lift figure. The other 5 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 +18 percentage points is the difference between those two pass rates over the 17 comparable cases. 4 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.