# Interdisciplinary Research

> Cross-domain synthesis and connection-finding using analogical reasoning, boundary-spanning, and novel hypothesis generation by linking disparate fields. Use when exploring new ideas, finding unexpected connections, or synthesizing across disciplines.

- Skill: `myrgic/interdisciplinary-research` (Agent Skill)
- Install (CLI): `npx skillmds@latest add myrgic/interdisciplinary-research`
- Raw SKILL.md: https://api.skillmd.com/api/skills/myrgic/interdisciplinary-research/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: myrgic (https://skillmd.com/u/myrgic)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/myrgic/interdisciplinary-research

---


# Interdisciplinary Research Skill

Techniques for finding connections across domains and generating novel hypotheses.

## Analogical Reasoning Protocol

When encountering a problem in domain A:

1. **Abstract the structure**
   - What are the key entities?
   - What are the relationships?
   - What is being optimized/conserved?
   - What are the constraints?

2. **Search for structural parallels**
   - Where else do similar structures appear?
   - What fields have solved analogous problems?
   - What metaphors capture the essence?

3. **Map the analogy carefully**
   | Source Domain | Target Domain |
   |---------------|---------------|
   | Entity A | Entity X |
   | Relationship R | Relationship Y |
   | Constraint C | Constraint Z |

4. **Test the mapping**
   - Where does the analogy break down?
   - What does the source predict about the target?
   - Are the breakdowns informative?

## Cross-Domain Connection Patterns

### Shared Mathematical Structure
Many domains share underlying mathematics:

| Structure | Appears In |
|-----------|------------|
| Exponential decay | Radioactivity, learning curves, memory |
| Power laws | City sizes, word frequencies, earthquakes |
| Network topology | Social graphs, neural networks, ecosystems |
| Diffusion equations | Heat, information spread, population genetics |
| Optimization landscapes | Evolution, learning, market dynamics |

### Analogous Processes

| Process | Domain 1 | Domain 2 |
|---------|----------|----------|
| Selection pressure | Evolution | Market competition |
| Information compression | Neural coding | Data compression |
| Equilibrium seeking | Thermodynamics | Economics |
| Feedback loops | Control systems | Immune response |
| Phase transitions | Physics | Social movements |

## Hypothesis Generation Techniques

### Negation
Take an assumption and ask: what if the opposite were true?
- "Neurons compute" -> "Neurons don't compute, they filter"
- "More data is better" -> "More data is harmful after some point"

### Extreme Cases
Push parameters to limits:
- What if this process were infinitely fast?
- What if there were zero cost?
- What if the population were infinite?

### Mechanism Swap
Take the mechanism from field A, apply to field B:
- "What if immune systems used gradient descent?"
- "What if markets had error-correcting codes?"
- "What if memory worked like version control?"

### Missing Middle
If A causes C, what is B?
- Identify known correlations
- Generate candidate mechanisms
- Design experiments to distinguish

## Synthesis Protocol

When integrating insights from multiple domains:

1. **Gather perspectives**
   - What does each field say about this?
   - What terminology do they use?
   - What do they consider solved/open?

2. **Identify tensions**
   - Where do fields disagree?
   - Are disagreements real or terminological?
   - What would resolve the tension?

3. **Find the deeper pattern**
   - What is common across all perspectives?
   - What level of abstraction reveals unity?
   - Is there a framework that contains all as special cases?

4. **Generate novel predictions**
   - What does the synthesis predict that no single field predicts?
   - Where should we look for evidence?
   - What experiments would test the synthesis?

## Question Prompts for Connection-Finding

When stuck, ask:

- "What does this remind me of from [other field]?"
- "Who else has solved a problem like this?"
- "What if we approached this like a [physicist/biologist/economist] would?"
- "What is the dual of this concept?"
- "What would the inverse problem look like?"
- "If I had to explain this to someone from [field], what would I say?"

## Reading Across Boundaries

### Efficient Cross-Domain Learning

1. **Start with review papers** - Get the landscape fast
2. **Learn the vocabulary** - Same words often mean different things
3. **Find the canonical papers** - Every field has its founding texts
4. **Identify the open problems** - This is where you might contribute
5. **Talk to practitioners** - Written sources miss tacit knowledge

### Warning Signs of Bad Analogies

- Surface similarity only (both have "networks" does not mean they work the same)
- Ignoring scale differences (what works for 10 might not work for 10 million)
- Category errors (treating metaphors as mechanisms)
- Confirmation bias (only seeing what supports the mapping)

## Documenting Connections

When you find a promising connection, capture:

```markdown
## Connection: [Source] <-> [Target]

### The Analogy
[What maps to what]

### Why It Might Work
[Structural similarities, shared mathematics]

### Where It Breaks Down
[Known limits of the analogy]

### Predictions
[What this connection suggests we should observe]

### Tests
[How we could validate or falsify]

### References
[Key papers from both domains]
```