---
name: yogsoth-ai-argumentative-zoning
description: "Tactic: Label every sentence of one paper with its rhetorical role using Argumentative Zoning. Use when fixed rhetorical labels and cross-paper alignment matter."
license: "Apache-2.0"
metadata:
  decimalai-skill-id: "ae830d69-bf2f-4bca-835d-716bf60a7171"
  decimalai-version-id: "f2a418ee-b985-4508-8a0b-d7bdcb2a578e"
  decimalai-version: "1"
  decimalai-body-sha256: "5f7c40ebff6157d91137fc1de7a7e6ae30a50a241511d27631ced226c33f55b9"
  decimalai-name: "yogsoth-ai/argumentative-zoning"
  decimalai-format: "1"
  decimalai-invocation: "model"
  decimalai-category: "research"
  decimalai-source: "https://app.decimal.ai/s/yogsoth-ai-argumentative-zoning@1/SKILL.md"
---
# Argumentative Zoning

## Orchestration Pattern

1. Fetch the paper; stop on `not_found`.
2. Segment the requested scope with sentence granularity and preserve
   `{line, start, end}` offsets. Write `01-unit-segmentation.json`.
3. Classify every unit with `label_set: argumentative-zoning`,
   `hierarchy_toggle: false`, and `output_type: single_label`. Write
   `02-unit-classification.json`.

Use exactly AIM, BACKGROUND, OWN, CONTRAST, BASIS, TEXTUAL, and OTHER. Every
sentence receives one label; use OTHER rather than skipping an uncertain
unit. Narrow scopes are valid but not distributionally comparable to a
full-text run.

Report scope, sentence count, zone counts, empty zones, and both paths.