Extract and steel-man the core arguments supporting a given opinion cluster.
Scanned 6/1/2026
Install to Claude Code
Skills Directorynpx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill argument-extraction --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Argument Extraction?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/yogsoth-ai-argument-extraction)More formats (shields.io, HTML) on the badges page.
---
name: argument-extraction
description: Extract and steel-man the core arguments supporting a given opinion cluster.
execution: subagent
prompt: ./prompt.md
input: cluster, judgments[]
used-by: structured-consensus
---
# Argument Extraction
Extract the core arguments supporting a given opinion cluster and present them in their strongest possible form (steel-manned). Synthesizes reasoning from multiple perspectives within the cluster into coherent, well-structured arguments.
## Execution
Spawn a subagent that takes a cluster characterization and the relevant judgments, then produces a set of steel-manned arguments representing the cluster's position.
## Why Subagent
- Argument extraction requires careful synthesis across multiple inputs
- Steel-manning requires dedicated analytical attention
- Output feeds directly into disagreement-visualization
## HARD-GATE
Output MUST contain: at least 1 argument per cluster, each with `claim`, `evidence`, `reasoning`, and `strength` fields. Arguments must be steel-manned (strongest possible version).
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
