combinatorial-creativity

$npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/combinatorial-creativity

Generates novel concepts through advanced combinatorial creativity techniques

  • Solves creative ideation challenges by blending concepts and exploring design spaces
  • Leverages Fauconnier-Turner models, TRIZ, and bisociation principles
  • Analyzes inputs to select optimal strategies like blending or function recombination
  • Delivers emergent ideas through structured exploration and property synthesis
SKILL.md
.github/skills/combinatorial-creativityView on GitHub ↗
---
name: combinatorial-creativity
description: Combinatorial Creativity Campaign — produce emergent concepts via concept blending, multi-level bisociation, and function combination (Fauconnier-Turner)
execution: campaign
used-by: creative-ideation
---

# Combinatorial Creativity

Produce emergent concepts via concept blending, multi-level bisociation, and function combination (Fauconnier-Turner).

## Strategy Routing

| 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 |

## Manifest

### Strategies

| 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) |

### Tactics

| 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 |

### SOPs

| 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 |

## Budget Table

| 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 |

## MCP Tools

| 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 |

## Context Management

- Each strategy tracks its own budget via State Ledger
- Strategies MUST NOT exceed allocated budget
- Campaign monitors cumulative spend across all strategies
- If a strategy exhausts budget before meeting yield, escalate to campaign level for reallocation
- Prefer paper-overview over paper-research for initial exploration (lower cost)
- Emergent properties are the primary campaign-level quality metric

## Available Tactics

| 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 |

## Available SOPs

| 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 |
More from yogsoth-ai/de-anthropocentric-research-engine