Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cross-Domain Discovery Campaign — find transferable mechanisms from unrelated fields via bisociation, analogical transfer, random stimulus, and forced bridging
.claude/skills/yogsoth-ai-cross-domain-discovery/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 56% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 115% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 73% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 47% | 0% |
Find transferable mechanisms from unrelated fields via bisociation, analogical transfer, random stimulus, and forced bridging.
| Strategy | Signal Keywords | |----------|----------------| | facet-bisociation | bisociation, two matrices, Koestler, collision, unrelated frames | | analogical-transfer | analogy, structure-mapping, Gentner, source domain, relational similarity | | random-stimulus-entry | random, stimulus, serendipity, unexpected entry, lateral input | | forced-bridge-construction | force connection, bridge, unrelated technologies, deliberate link | | design-by-analogy | DBA, problem reframe, analogical design, bio-inspired, nature-inspired |
| Strategy | Description | |----------|-------------| | facet-bisociation | Bridge two unrelated thinking matrices via Koestler bisociation | | analogical-transfer | Systematic structure-mapping from source to target domain (Gentner) | | random-stimulus-entry | Random word/paper/concept as thinking entry point | | forced-bridge-construction | Force connections between unrelated technologies | | design-by-analogy | Complete DBA process: problem reframe → source search → map → transfer → adapt |
| Tactic | Description | |--------|-------------| | analogy-extraction | Extract transferable structural principles from source domains (shared) | | domain-divergence | Scan and select maximally diverse source domains | | bridge-validation | Validate analogy depth and transfer viability |
| SOP | Description | |-----|-------------| | abstraction-extraction | Extract abstract principles from concrete domain cases | | structural-mapping | Map source→target structural correspondences | | random-paper-entry | Select random paper facet as creative stimulus | | forced-connection | Force connection between two unrelated concepts | | transfer-adaptation | Adapt transferred principle to target problem constraints | | analogy-quality-assessment | Assess analogy depth (surface/structural/systemic) | | bisociation-network-construction | Build multi-domain bridging concept network | | cross-domain-synthesis | Synthesize all cross-domain findings |
| Strategy | web-search | web-research | paper-overview | paper-search | paper-research | |----------|-----------|-------------|---------------|-------------|---------------| | facet-bisociation | 30 | 10 | 25 | 15 | 5 | | analogical-transfer | 25 | 10 | 30 | 20 | 8 | | random-stimulus-entry | 20 | 5 | 15 | 10 | 3 | | forced-bridge-construction | 25 | 8 | 20 | 12 | 5 | | design-by-analogy | 30 | 10 | 30 | 20 | 10 |
| Tool | Server | Purpose | |------|--------|---------| | brave_web_search | brave-search | General web search for cross-domain solutions | | 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 in distant domains | | relevanceSearch | semantic-scholar | Search academic literature across fields | | paper | semantic-scholar | Get paper details | | citations | semantic-scholar | Trace citation networks across domains |
| Tactic | Role | |--------|------| | analogy-extraction | Extract transferable structural principles (shared, from campaign 2) | | domain-divergence | Ensure source domain diversity and maximize transfer potential | | bridge-validation | Validate analogy depth before committing to transfer |
| SOP | Role | |-----|------| | abstraction-extraction | Extract abstract principles from concrete cases | | structural-mapping | Map source→target structural correspondences | | random-paper-entry | Random paper facet as creative stimulus | | forced-connection | Force connection between unrelated concepts | | transfer-adaptation | Adapt transferred principle to target constraints | | analogy-quality-assessment | Assess analogy depth and transfer risk | | bisociation-network-construction | Build multi-domain bridging network | | cross-domain-synthesis | Synthesize all cross-domain findings into report |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Strategy | When to use | | --- | --- | | analogical-transfer | Systematic structure-mapping from source to target domain (Gentner). Identify relational correspondences and transfer higher-order constraints. | | design-by-analogy | Complete DBA process: problem reframe → source search → map → transfer → adapt. Full Design-by-Analogy methodology for systematic analogical design. | | facet-bisociation | Bridge two unrelated thinking matrices via Koestler bisociation. Identify independent frames of reference and force collision to produce creative insight. | | forced-bridge-construction | Force connections between unrelated technologies. Deliberately construct bridges where none naturally exist to discover novel integration possibilities. | | random-stimulus-entry | Random word/paper/concept as thinking entry point. Use genuine randomness to escape fixation and open unexpected solution paths. |
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | analogy-extraction | Extract transferable structural principles from source domains. Orchestrates source identification → abstraction → structural mapping → transfer validation. | | bridge-validation | Validate analogy depth and transfer viability. Ensures only deep structural analogies (not surface-level similarities) proceed to transfer. | | creative-ideation-provocation-generation | Generate PO provocations and extract constructive movement. Orchestrates assumption surfacing → provocation creation → movement extraction → idea formation. | | domain-divergence | Scan and select maximally diverse source domains. Ensures creative search covers genuinely unrelated fields with high transfer potential. | | 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-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. | | bisociation-network-construction | Build multi-domain bridging concept network. Creates a network of collision points between multiple thinking matrices. | | 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. | | cross-domain-synthesis | Synthesize all cross-domain findings into a structured idea report. Integrates outputs from all strategies and SOPs. | | domain-scanning | Scan distant domains for transferable principles. Uses web-search and paper-overview to identify analogous solutions in unrelated fields. | | forced-connection | Force connection between two unrelated concepts. Deliberately construct bridging paths where no natural connection exists. | | idea-synthesis | Synthesize diverse ideas into coherent solution concepts. Combines fragments from multiple ideation passes into structured, actionable ideas with clear mechanism descriptions. | | random-paper-entry | Select random paper facet as creative stimulus. Uses genuine randomness in paper selection to break domain fixation. | | random-word-stimulus | Use random word/concept injection as creative stimulus. Selects random concepts and forces connection to the problem space, generating unexpected solution paths. | | 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-02 | fail→fail | 26,914 | 14,024 | -48% | 1 | 1 | 0% | 4,038 | 2,881 | -29% | 0 | 0 | — |
case-01 | pass→fail | 39,663 | 8,036 | -80% | 1 | 1 | 0% | 6,222 | 2,722 | -56% | 0 | 0 | — |
case-03 | fail→fail | 13,902 | 19,323 | +39% | 1 | 1 | 0% | 2,339 | 5,192 | +122% | 0 | 0 | — |
case-04 | pass→fail | 29,571 | 8,677 | -71% | 1 | 1 | 0% | 5,187 | 2,516 | -51% | 0 | 0 | — |
case-05 | pass→fail | 27,396 | 31,964 | +17% | 1 | 1 | 0% | 4,433 | 8,223 | +85% | 0 | 0 | — |
case-06 | fail→pass | 42,671 | 4,667 | -89% | 1 | 1 | 0% | 1,887 | 2,948 | +56% | 0 | 0 | — |
case-07 | fail→fail | 22,706 | 6,799 | -70% | 1 | 1 | 0% | 3,501 | 3,223 | -8% | 0 | 0 | — |
case-08 | fail→pass | 17,453 | 2,269 | -87% | 1 | 1 | 0% | 2,589 | 2,457 | -5% | 0 | 0 | — |
case-09 | pass→pass | 10,861 | 4,055 | -63% | 1 | 1 | 0% | 1,595 | 2,666 | +67% | 0 | 0 | — |
case-10 | pass→pass | 13,758 | 3,377 | -75% | 1 | 1 | 0% | 1,907 | 2,527 | +33% | 0 | 0 | — |
case-11 | fail→pass | 13,528 | 2,307 | -83% | 1 | 1 | 0% | 1,122 | 2,417 | +115% | 0 | 0 | — |
case-12 | fail→pass | 9,970 | 3,950 | -60% | 1 | 1 | 0% | 1,494 | 2,579 | +73% | 0 | 0 | — |
case-13 | pass→pass | 14,760 | 3,041 | -79% | 1 | 1 | 0% | 2,212 | 2,560 | +16% | 0 | 0 | — |
case-14 | pass→pass | 18,926 | 6,477 | -66% | 1 | 1 | 0% | 2,864 | 3,103 | +8% | 0 | 0 | — |
case-15 | fail→pass | 14,127 | 6,977 | -51% | 1 | 1 | 0% | 2,192 | 3,212 | +47% | 0 | 0 | — |
case-16 | pass→pass | 17,657 | 3,672 | -79% | 1 | 1 | 0% | 2,586 | 2,547 | -2% | 0 | 0 | — |
case-17 | pass→pass | 27,691 | 4,377 | -84% | 1 | 1 | 0% | 4,268 | 2,827 | -34% | 0 | 0 | — |
case-18 | pass→pass | 20,308 | 4,014 | -80% | 1 | 1 | 0% | 1,860 | 2,609 | +40% | 0 | 0 | — |
case-19 | pass→pass | 12,407 | 3,353 | -73% | 1 | 1 | 0% | 1,884 | 2,538 | +35% | 0 | 0 | — |
case-20 | pass→pass | 24,743 | 3,469 | -86% | 1 | 1 | 0% | 2,282 | 2,648 | +16% | 0 | 0 | — |
case-21 | fail→pass | 7,315 | 2,296 | -69% | 1 | 1 | 0% | 1,084 | 2,396 | +121% | 0 | 0 | — |
case-22 | pass→pass | 6,761 | 2,251 | -67% | 1 | 1 | 0% | 1,010 | 2,407 | +138% | 0 | 0 | — |
case-23 | pass→pass | 9,323 | 2,525 | -73% | 1 | 1 | 0% | 1,441 | 2,445 | +70% | 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. 23 cases were attempted, and 19 counted toward the lift figure. The other 4 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 +13 percentage points is the difference between those two pass rates over the 19 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.