# Debate Transcript Analysis

> Extracts key turning points, patterns, and insights from completed debate transcripts. Produces structured summary for verdict synthesis.

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

---


# Debate Transcript Analysis

Extracts key turning points from completed debates.

## Execution

Subagent — spawned via subagent-spawning/spawn-agent.

## Why Subagent

Post-debate analysis requires reviewing the full transcript with fresh eyes — isolated context prevents anchoring to any single round's perspective.

## Input

- **full_transcript**: Complete debate transcript (all rounds)
- **round_verdicts**: All judge verdicts
- **final_confidence**: Final calibrated confidence score

## Output

- **turning_points**: Moments where the debate shifted significantly
- **key_vulnerabilities**: Most impactful weaknesses identified
- **strongest_defenses**: Most effective counter-arguments
- **unresolved_tensions**: Issues that remained contested
- **summary**: Concise narrative of the debate arc

## Budget

One unit = one transcript analysis per completed debate.

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

## Available SOPs

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

| SOP | When to use |
| --- | --- |
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |

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