# Debate Adjudication Voting

> Independent agents score rubric dimensions with written ballots; synthesis agent explains weighting. Use for high-stakes evaluation. Scope boundary: counterpoint generation → `counterpoint-perspectives`; wine blend → `wine-blending-fusion`.

- Skill: `catcorner22/debate-adjudication-voting` (Agent Skill)
- Install (CLI): `npx skillmds@latest add catcorner22/debate-adjudication-voting`
- Raw SKILL.md: https://api.skillmd.com/api/skills/catcorner22/debate-adjudication-voting/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: CatCorner22 (https://skillmd.com/u/catcorner22)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/catcorner22/debate-adjudication-voting

---

# Debate adjudication multi-agent voting

**#27** · **Domain:** Competitive debate · **Category:** refinement · **Difficulty:** 🔴 High

## Core principle

Discrete criteria scored separately with ballot justification.

## AI problem addressed

Single-pass 'sounds good' evaluation hides tradeoffs.

## Implementation

Agent A: logic 1–10 + justification
Agent B: evidence 1–10 + justification
Agent C: completeness 1–10 + justification
Synthesis: final score + which dimension drove decision and why

## Boundaries

- Prototype as prompt scaffold (🟢) before full pipeline middleware (🟡/🔴)
- Category router: **`ai-transfer-refinement`**
- Catalog: **`ai-transfer-ecosystem-primer`**
- Runtime plugin id: `debate_judging`