---
name: yogsoth-ai/unit-segmentation
source: https://app.decimal.ai/s/yogsoth-ai-unit-segmentation@1/SKILL.md
source_sha256: db1b73a9b295
---

# Unit Segmentation

Splits text into labeling units (sentence or clause granularity, scoped to full text/abstract/intro) — pure segmentation, no labeling.

## Execution

Subagent — spawned via spawn-agent skill.

## Why This Exists As Its Own Step

7 different classification methods (AZ, CoreSC, PubMed-RCT, NICTA-PIBOSO, CSAbstruct, CODA-19, Swales) all need pre-segmented units but disagree on granularity and scope — factoring segmentation out once, parameterized, avoids duplicating this logic inside `unit-classification` seven times over (graph correction L17/L18: the original graph was missing this step entirely, silently assuming pre-segmented input existed).

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

## Available SOPs

| SOP | When to use |
| --- | --- |
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. |

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