Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Systematic structure-mapping from source to target domain (Gentner). Identify relational correspondences and transfer higher-order constraints.
.claude/skills/yogsoth-ai-analogical-transfer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 69% | 0% |
| case-21 | ✗→✓ | ▲ Improved | -27% | 0% |
| case-01 | ✓→✗ | ▼ Worse | 85% | 0% |
Systematic structure-mapping from source to target domain following Gentner's structure-mapping theory. Prioritize relational similarity over surface similarity.
| Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 25 | 0 | 0% | | web-research | 10 | 0 | 0% | | paper-overview | 30 | 0 | 0% | | paper-search | 20 | 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 | |--------|------| | analogy-extraction | Core tactic — extract and validate structural analogies | | domain-divergence | Find distant source domains with high structural similarity | | bridge-validation | Validate mapping depth before transfer |
| SOP | Role | |-----|------| | domain-scanning | Find candidate source domains | | abstraction-extraction | Extract abstract relational structure | | structural-mapping | Map source→target correspondences | | analogy-quality-assessment | Rate analogy depth (surface/structural/systemic) | | transfer-adaptation | Adapt transferred principle to target constraints | | cross-domain-synthesis | Synthesize transfer outputs |
<!-- 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. | | analogy-quality-assessment | Assess analogy depth (surface/structural/systemic). Determines whether an analogy warrants transfer investment. | | cross-domain-synthesis | Synthesize all cross-domain findings into a structured idea report. Integrates outputs from all strategies and SOPs. | | structural-mapping | Map source→target structural correspondences. Identifies corresponding, missing, and extra elements between domains. | | transfer-adaptation | Adapt transferred principle to target problem constraints. Produces concrete adapted solutions from abstract principles. |
<!-- 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→fail | 11,579 | 16,364 | +41% | 1 | 1 | 0% | 1,631 | 3,011 | +85% | 0 | 0 | — |
case-02 | pass→pass | 16,068 | 17,403 | +8% | 1 | 1 | 0% | 2,714 | 3,584 | +32% | 0 | 0 | — |
case-03 | pass→pass | 7,899 | 7,487 | -5% | 1 | 1 | 0% | 1,545 | 2,278 | +47% | 0 | 0 | — |
case-04 | pass→pass | 14,753 | 13,207 | -10% | 1 | 1 | 0% | 2,049 | 2,678 | +31% | 0 | 0 | — |
case-05 | pass→pass | 14,561 | 15,601 | +7% | 1 | 1 | 0% | 1,917 | 2,975 | +55% | 0 | 0 | — |
case-06 | pass→fail | 18,537 | 23,958 | +29% | 1 | 1 | 0% | 2,527 | 4,304 | +70% | 0 | 0 | — |
case-07 | fail→pass | 8,675 | 6,152 | -29% | 1 | 1 | 0% | 1,234 | 1,733 | +40% | 0 | 0 | — |
case-08 | fail→pass | 15,499 | 2,014 | -87% | 1 | 1 | 0% | 935 | 1,062 | +14% | 0 | 0 | — |
case-09 | pass→pass | 10,461 | 18,310 | +75% | 1 | 1 | 0% | 1,527 | 3,293 | +116% | 0 | 0 | — |
case-10 | pass→pass | 22,626 | 36,043 | +59% | 1 | 1 | 0% | 2,976 | 4,905 | +65% | 0 | 0 | — |
case-11 | pass→pass | 13,630 | 4,739 | -65% | 1 | 1 | 0% | 1,811 | 1,492 | -18% | 0 | 0 | — |
case-12 | pass→pass | 10,208 | 11,767 | +15% | 1 | 1 | 0% | 1,436 | 2,562 | +78% | 0 | 0 | — |
case-13 | fail→pass | 21,049 | 29,973 | +42% | 1 | 1 | 0% | 3,089 | 5,211 | +69% | 0 | 0 | — |
case-14 | pass→pass | 8,591 | 8,874 | +3% | 1 | 1 | 0% | 1,176 | 1,997 | +70% | 0 | 0 | — |
case-15 | pass→pass | 14,805 | 16,155 | +9% | 1 | 1 | 0% | 2,257 | 3,022 | +34% | 0 | 0 | — |
case-16 | pass→pass | 14,050 | 12,590 | -10% | 1 | 1 | 0% | 2,048 | 2,625 | +28% | 0 | 0 | — |
case-17 | pass→pass | 5,507 | 3,592 | -35% | 1 | 1 | 0% | 818 | 1,313 | +61% | 0 | 0 | — |
case-18 | pass→pass | 15,551 | 21,422 | +38% | 1 | 1 | 0% | 2,256 | 3,829 | +70% | 0 | 0 | — |
case-19 | pass→pass | 16,602 | 11,915 | -28% | 1 | 1 | 0% | 2,371 | 2,544 | +7% | 0 | 0 | — |
case-20 | pass→pass | 15,102 | 9,577 | -37% | 1 | 1 | 0% | 2,072 | 2,331 | +13% | 0 | 0 | — |
case-21 | fail→pass | 11,562 | 2,667 | -77% | 1 | 1 | 0% | 1,651 | 1,197 | -27% | 0 | 0 | — |
case-22 | pass→pass | 12,512 | 17,334 | +39% | 1 | 1 | 0% | 1,760 | 3,095 | +76% | 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 +9 percentage points is the difference between those two pass rates over the 22 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.