domain-divergence

$npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/domain-divergence

Scan and select maximally diverse source domains to maximize creative potential.

SKILL.md
.github/skills/domain-divergenceView on GitHub ↗
---
name: domain-divergence
description: Scan and select maximally diverse source domains. Ensures creative search covers genuinely unrelated fields with high transfer potential.
execution: tactic
used-by: cross-domain-discovery, facet-bisociation, analogical-transfer, random-stimulus-entry, forced-bridge-construction, design-by-analogy
---

# Domain Divergence

Scan and select maximally diverse source domains to maximize creative potential.

## Stages

### Stage 1: Domain Scanning

Use domain-scanning SOP to identify candidate source domains. Cast a wide net across sciences, arts, engineering, biology, social systems, mathematics, and everyday life.

### Stage 2: Random Paper Entry

Inject randomness via random-paper-entry SOP. Select papers from unexpected fields to break domain fixation and discover overlooked source domains.

### Stage 3: Random Word Stimulus

Use random-word-stimulus SOP to generate additional domain candidates that pure search would miss. Random words point to concrete domains (e.g., "coral" → marine biology → reef self-organization).

### Stage 4: Evaluate Diversity

Assess the collected domains for genuine diversity:
- No two domains should share the same parent discipline
- Domains should span at least 3 of: natural science, social science, engineering, arts, mathematics, everyday life
- Each domain must have identifiable transfer potential to the target problem

## Minimum Yield

| Metric | Floor |
|--------|-------|
| Domains scanned | ≥8 |
| Unrelated domains identified | ≥3 |
| Domains with transfer potential | ≥3 |
| Discipline categories covered | ≥3 |

## Available SOPs

| SOP | Role |
|-----|------|
| domain-scanning | Stage 1 — systematic domain search |
| random-paper-entry | Stage 2 — random paper as domain pointer |
| random-word-stimulus | Stage 3 — random word as domain pointer |
| abstraction-extraction | Stage 4 — verify transfer potential via abstraction |
| analogy-quality-assessment | Stage 4 — assess structural similarity depth |
More from yogsoth-ai/de-anthropocentric-research-engine