Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Combinatorial Creativity Campaign — produce emergent concepts via concept blending, multi-level bisociation, and function combination (Fauconnier-Turner)
.claude/skills/yogsoth-ai-combinatorial-creativity/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 135% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 83% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 44% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 105% | 0% |
Produce emergent concepts via concept blending, multi-level bisociation, and function combination (Fauconnier-Turner).
| Strategy | Signal Keywords | |----------|----------------| | concept-blending | blend, Fauconnier, Turner, 4-space, input space, generic space, blended space | | multi-level-bisociation | bisociation, abstraction levels, multi-level, collision, Koestler | | design-space-exploration | parametric, constraint satisfaction, combinatorial search, design space | | function-combination | TRIZ, function, recombination, redistribution, function model | | emergent-property-hunting | emergence, non-additive, synergy, novel property, combination effect |
| Strategy | Description | |----------|-------------| | concept-blending | Fauconnier-Turner 4-space model: Generic + Input1 + Input2 → Blended Space | | multi-level-bisociation | Simultaneous concept collision at multiple abstraction levels | | design-space-exploration | Parametric variation + constraint satisfaction combinatorial search | | function-combination | TRIZ function analysis: function-level recombination and redistribution | | emergent-property-hunting | Seek properties that emerge from combination (non-additive) |
| Tactic | Description | |--------|-------------| | combination-mapping | Systematically enumerate parameter dimensions and generate viable combinations (shared) | | blend-construction | Construct complete 4-space blends with emergent structure | | emergence-detection | Detect and validate emergent properties from combinations |
| SOP | Description | |-----|-------------| | input-space-construction | Build input spaces for two source concepts | | generic-space-extraction | Extract shared abstract structure from two input spaces | | 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 15 vital relations between concepts | | abstraction-ladder | Perform bisociation at multiple abstraction levels | | function-redistribution | Redistribute functions across different components | | emergent-property-identification | Identify non-additive properties from combinations | | combinatorial-synthesis | Synthesize all combinatorial creativity outputs |
| Strategy | web-search | web-research | paper-overview | paper-search | paper-research | |----------|-----------|-------------|---------------|-------------|---------------| | concept-blending | 25 | 10 | 30 | 20 | 10 | | multi-level-bisociation | 25 | 10 | 25 | 15 | 8 | | design-space-exploration | 20 | 8 | 20 | 12 | 5 | | function-combination | 20 | 8 | 20 | 12 | 5 | | emergent-property-hunting | 25 | 10 | 25 | 15 | 8 |
| Tool | Server | Purpose | |------|--------|---------| | brave_web_search | brave-search | General web search for combinatorial concepts | | brave_llm_context | brave-search | Deep content extraction from web pages | | apify/rag-web-browser | apify | Full page scraping for detailed content | | get_paper_content | alphaxiv | Read academic paper content | | discover_papers | alphaxiv | Find research papers on blending/combination | | relevanceSearch | semantic-scholar | Search academic literature | | paper | semantic-scholar | Get paper details | | citations | semantic-scholar | Trace citation networks |
| Tactic | Role | |--------|------| | combination-mapping | Systematically enumerate parameter dimensions and generate viable combinations (shared) | | blend-construction | Construct complete 4-space blends with emergent structure | | emergence-detection | Detect and validate emergent properties from combinations |
| SOP | Role | |-----|------| | input-space-construction | Build input spaces for two source concepts | | generic-space-extraction | Extract shared abstract structure from two input spaces | | 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 15 vital relations between concepts | | abstraction-ladder | Perform bisociation at multiple abstraction levels | | function-redistribution | Redistribute functions across different components | | emergent-property-identification | Identify non-additive properties from combinations | | combinatorial-synthesis | Synthesize all combinatorial creativity outputs |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Strategy | When to use | | --- | --- | | concept-blending | Fauconnier-Turner 4-space model: Generic + Input1 + Input2 → Blended Space | | design-space-exploration | Parametric variation + constraint satisfaction combinatorial search | | emergent-property-hunting | Seek properties that emerge from combination (non-additive) | | function-combination | TRIZ function analysis: function-level recombination and redistribution | | multi-level-bisociation | Simultaneous concept collision at multiple abstraction levels |
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. | | creative-ideation-combination-mapping | Systematically enumerate parameter dimensions and generate viable combinations. Orchestrates parameter extraction → value enumeration → compatibility assessment → synthesis. | | emergence-detection | Detect and validate emergent properties from combinations. Orchestrates emergent-property-identification → blend-elaboration. | | evaluation-filtering | Multi-dimensional evaluation and tiered filtering of generated ideas. Orchestrates novelty assessment → feasibility check → ranking → selection. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | abstraction-ladder | Perform bisociation at multiple abstraction levels | | 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 | | context-checkpoint | Append research process and results to the current Phase's context file. Covers both process and results with genuine substance. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase. | | context-init | Create a new context file for a research Phase. Called once at Phase start to initialize the file that subsequent context-checkpoint calls will append to. Use this skill whenever a new research Phase begins and a fresh context file is needed. | | creative-ideation-novelty-scoring | Score ideas on novelty dimensions — structural distance from known solutions, conceptual surprise, domain-crossing depth. Produces ranked novelty assessment. | | creative-ideation-saturation-detection | Determine when additional ideation yields diminishing returns. Analyzes latest idea batch against existing corpus to judge continue/near-saturation/saturated. | | domain-scanning | Scan distant domains for transferable principles. Uses web-search and paper-overview to identify analogous solutions in unrelated fields. | | emergent-property-identification | Identify non-additive properties from combinations | | function-redistribution | Redistribute functions across different components | | generic-space-extraction | Extract shared abstract structure from two input spaces | | idea-synthesis | Synthesize diverse ideas into coherent solution concepts. Combines fragments from multiple ideation passes into structured, actionable ideas with clear mechanism descriptions. | | input-space-construction | Build input spaces for two source concepts | | parameter-identification | Identify the key parameters/dimensions of a problem space. Produces a structured parameter list with value ranges for morphological analysis. | | 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 | pass→pass | 12,831 | 4,967 | -61% | 1 | 1 | 0% | 2,010 | 2,891 | +44% | 0 | 0 | — |
case-02 | pass→pass | 17,452 | 11,197 | -36% | 1 | 1 | 0% | 2,766 | 3,824 | +38% | 0 | 0 | — |
case-03 | fail→pass | 7,096 | 4,274 | -40% | 1 | 1 | 0% | 1,120 | 2,636 | +135% | 0 | 0 | — |
case-04 | fail→pass | 13,738 | 3,329 | -76% | 1 | 1 | 0% | 2,208 | 2,485 | +13% | 0 | 0 | — |
case-05 | pass→pass | 13,667 | 2,940 | -78% | 1 | 1 | 0% | 2,011 | 2,371 | +18% | 0 | 0 | — |
case-06 | fail→pass | 8,089 | 1,855 | -77% | 1 | 1 | 0% | 1,199 | 2,190 | +83% | 0 | 0 | — |
case-07 | pass→pass | 11,890 | 1,965 | -83% | 1 | 1 | 0% | 1,855 | 2,305 | +24% | 0 | 0 | — |
case-08 | pass→pass | 11,440 | 7,206 | -37% | 1 | 1 | 0% | 2,078 | 3,244 | +56% | 0 | 0 | — |
case-09 | fail→pass | 13,288 | 6,729 | -49% | 1 | 1 | 0% | 2,130 | 3,068 | +44% | 0 | 0 | — |
case-10 | fail→pass | 10,548 | 10,731 | +2% | 1 | 1 | 0% | 1,801 | 3,696 | +105% | 0 | 0 | — |
case-11 | fail→pass | 9,498 | 4,637 | -51% | 1 | 1 | 0% | 1,366 | 2,681 | +96% | 0 | 0 | — |
case-12 | pass→pass | 13,542 | 4,022 | -70% | 1 | 1 | 0% | 2,091 | 2,560 | +22% | 0 | 0 | — |
case-13 | fail→pass | 11,982 | 2,719 | -77% | 1 | 1 | 0% | 1,893 | 2,318 | +22% | 0 | 0 | — |
case-14 | fail→fail | 9,006 | 3,518 | -61% | 1 | 1 | 0% | 1,490 | 2,483 | +67% | 0 | 0 | — |
case-15 | fail→pass | 16,971 | 4,772 | -72% | 1 | 1 | 0% | 2,723 | 2,722 | -0% | 0 | 0 | — |
case-16 | fail→pass | 6,867 | 2,378 | -65% | 1 | 1 | 0% | 1,151 | 2,339 | +103% | 0 | 0 | — |
case-17 | fail→pass | 7,852 | 2,580 | -67% | 1 | 1 | 0% | 1,165 | 2,278 | +96% | 0 | 0 | — |
case-18 | fail→pass | 9,455 | 2,036 | -78% | 1 | 1 | 0% | 1,357 | 2,236 | +65% | 0 | 0 | — |
case-19 | pass→pass | 9,677 | 2,395 | -75% | 1 | 1 | 0% | 1,477 | 2,296 | +55% | 0 | 0 | — |
case-20 | fail→fail | 12,901 | 8,325 | -35% | 1 | 1 | 0% | 2,454 | 3,420 | +39% | 0 | 0 | — |
case-21 | fail→fail | 16,566 | 13,704 | -17% | 1 | 1 | 0% | 2,855 | 4,279 | +50% | 0 | 0 | — |
case-22 | fail→fail | 8,601 | 17,910 | +108% | 1 | 1 | 0% | 1,597 | 4,912 | +208% | 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 +50 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.