Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Fauconnier-Turner 4-space model: Generic + Input1 + Input2 → Blended Space
.claude/skills/yogsoth-ai-concept-blending/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -4% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -1% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -5% | 0% |
Fauconnier-Turner 4-space model: Generic + Input1 + Input2 → Blended Space. Produce novel concepts by selectively projecting structure from two input mental spaces into a blended space that develops emergent structure.
| 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 | 10 | 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 blend dimensions and viable combinations | | blend-construction | Construct complete 4-space blends with emergent structure | | emergence-detection | Detect emergent properties in completed blends |
| SOP | Role | |-----|------| | input-space-construction | Build input spaces for source concepts | | generic-space-extraction | Extract shared abstract structure | | blend-composition | Compose new connections in blended space | | blend-completion | Complete blend with background knowledge | | blend-elaboration | Run blend as mental simulation | | vital-relation-mapping | Map vital relations between concepts | | combinatorial-synthesis | Synthesize blending 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 | | --- | --- | | blend-completion | Complete blend with background knowledge | | blend-composition | Compose new connections in blended space | | blend-elaboration | Run blend as mental simulation | | combinatorial-synthesis | Synthesize all combinatorial creativity outputs | | generic-space-extraction | Extract shared abstract structure from two input spaces | | input-space-construction | Build input spaces for two source concepts | | 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→pass | 10,641 | 3,990 | -63% | 1 | 1 | 0% | 1,705 | 1,425 | -16% | 0 | 0 | — |
case-02 | pass→pass | 7,495 | 9,567 | +28% | 1 | 1 | 0% | 1,287 | 2,175 | +69% | 0 | 0 | — |
case-03 | pass→pass | 7,541 | 10,220 | +36% | 1 | 1 | 0% | 1,209 | 2,480 | +105% | 0 | 0 | — |
case-04 | pass→pass | 10,515 | 11,163 | +6% | 1 | 1 | 0% | 1,762 | 2,701 | +53% | 0 | 0 | — |
case-05 | pass→pass | 5,428 | 4,634 | -15% | 1 | 1 | 0% | 828 | 1,451 | +75% | 0 | 0 | — |
case-06 | pass→pass | 14,659 | 14,022 | -4% | 1 | 1 | 0% | 2,225 | 2,935 | +32% | 0 | 0 | — |
case-07 | fail→pass | 10,716 | 4,762 | -56% | 1 | 1 | 0% | 1,692 | 1,617 | -4% | 0 | 0 | — |
case-08 | fail→pass | 10,185 | 6,813 | -33% | 1 | 1 | 0% | 1,588 | 2,057 | +30% | 0 | 0 | — |
case-09 | fail→pass | 6,936 | 1,960 | -72% | 1 | 1 | 0% | 1,047 | 1,039 | -1% | 0 | 0 | — |
case-10 | fail→pass | 7,307 | 1,644 | -78% | 1 | 1 | 0% | 1,081 | 1,027 | -5% | 0 | 0 | — |
case-11 | fail→pass | 9,819 | 1,641 | -83% | 1 | 1 | 0% | 1,396 | 910 | -35% | 0 | 0 | — |
case-12 | fail→pass | 2,068 | 1,827 | -12% | 1 | 1 | 0% | 266 | 977 | +267% | 0 | 0 | — |
case-13 | fail→pass | 4,684 | 1,608 | -66% | 1 | 1 | 0% | 708 | 1,010 | +43% | 0 | 0 | — |
case-18 | pass→fail | 10,573 | 2,310 | -78% | 1 | 1 | 0% | 1,574 | 1,114 | -29% | 0 | 0 | — |
case-14 | pass→pass | 12,614 | 14,223 | +13% | 1 | 1 | 0% | 1,854 | 2,901 | +56% | 0 | 0 | — |
case-15 | fail→pass | 6,244 | 15,134 | +142% | 1 | 1 | 0% | 1,199 | 3,441 | +187% | 0 | 0 | — |
case-16 | fail→pass | 7,506 | 2,954 | -61% | 1 | 1 | 0% | 1,166 | 1,271 | +9% | 0 | 0 | — |
case-17 | pass→fail | 7,462 | 2,386 | -68% | 1 | 1 | 0% | 1,150 | 1,137 | -1% | 0 | 0 | — |
case-19 | pass→pass | 6,025 | 11,437 | +90% | 1 | 1 | 0% | 967 | 2,430 | +151% | 0 | 0 | — |
case-20 | pass→pass | 18,881 | 27,633 | +46% | 1 | 1 | 0% | 2,876 | 5,361 | +86% | 0 | 0 | — |
case-21 | pass→pass | 14,136 | 20,297 | +44% | 1 | 1 | 0% | 2,362 | 4,204 | +78% | 0 | 0 | — |
case-22 | pass→fail | 12,650 | 28,416 | +125% | 1 | 1 | 0% | 2,065 | 5,040 | +144% | 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 +32 percentage points is the difference between those two pass rates over the 22 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.