# Hypothesis Formation Novelty Scoring

> SOP: Assess the novelty potential of a research gap, identify differentiation directions, and output a score

- Skill: `yogsoth-ai/hypothesis-formation-novelty-scoring` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add yogsoth-ai/hypothesis-formation-novelty-scoring`
- Raw SKILL.md: https://api.skillmd.com/api/skills/yogsoth-ai/hypothesis-formation-novelty-scoring/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: yogsoth-ai (https://skillmd.com/u/yogsoth-ai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/yogsoth-ai/hypothesis-formation-novelty-scoring

---


# Novelty Scoring

Assess the novelty potential of a research gap, identify differentiation directions, and output a score.

## HARD-GATE

<HARD-GATE>
- Input must be a GapRecord with status: "complete"
- The output composite score must be within the interval [1, 5]
- The differentiation_directions list must not be empty (at least 1 entry)
- Each sub-dimension must be accompanied by at least 1 sentence of textual rationale
</HARD-GATE>

## Pipeline

1. **Precondition check**: Verify the completeness of the input GapRecord; extract keywords for literature scanning
2. **Existing-work scan**: Use literature-engine and web-browsing to retrieve recent work (past 3 years) directly related to the gap; record existing solutions and partial solutions
3. **Differentiation-space identification**: Compare existing work against the gap's full requirements to identify angles not yet covered (methods, data, problem setup, evaluation dimensions, etc.)
4. **Innovation-potential assessment**: Judge the likelihood of producing a genuinely novel contribution within the differentiation space (1-5); consider: size of the white space, competition density
5. **Frontier assessment**: Judge whether the gap is at the frontier of the field rather than already well-studied (1-5)
6. **Composite scoring**: Equal-weight average of the two dimensions, keeping one decimal place; list specific differentiation directions
7. **Output**: Return the NoveltyScore object

## Output Format

```json
{
  "gap_id": "gap_001",
  "existing_work_summary": "Brief summary of existing work (2-3 sentences)",
  "dimension_scores": {
    "innovation_potential": { "score": 4, "rationale": "..." },
    "frontier_position": { "score": 4, "rationale": "..." }
  },
  "composite_score": 4.0,
  "differentiation_directions": [
    "Direction 1: ...",
    "Direction 2: ..."
  ],
  "overall_rationale": "Overall basis (2-4 sentences)"
}
```

<!-- BEGIN available-tables (generated) -->

## Available SOPs

Optional, no fixed order; the final leaf is always a sop.

| SOP | When to use |
| --- | --- |
| hypothesis-formation-paper-research | Import SOP: Deep literature research, raw full text + PDF Q&A (from literature-engine) |
| hypothesis-formation-paper-search | Import SOP: Medium-depth literature search, AI summary report (from literature-engine) |
| hypothesis-formation-web-research | Import SOP: deep web research, full-text fetching and analysis (from web-browsing) |
| hypothesis-formation-web-search | Import SOP: quick web scan, discover URLs and snippets (from web-browsing) |

<!-- END available-tables (generated) -->