Responds to attacks with counter-evidence and counter-arguments. Defends artifact using evidence, clarification, and rebuttal while acknowledging valid criticisms.
Scanned 6/1/2026
Install to Claude Code
Skills Directorynpx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill debate-defender --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Debate Defender?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/yogsoth-ai-debate-defender)More formats (shields.io, HTML) on the badges page.
---
name: debate-defender
description: Responds to attacks with counter-evidence and counter-arguments. Defends artifact using evidence, clarification, and rebuttal while acknowledging valid criticisms.
execution: subagent
prompt: ./prompt.md
input: artifact (string), attacks (string), previous_defenses (string)
used-by: [multiagent-debate]
---
# Debate Defender
Responds to structured attacks with counter-evidence and rebuttals.
## Execution
Subagent — spawned via subagent-spawning/spawn-agent.
## Why Subagent
Defense requires dedicated advocacy stance. Isolated context prevents premature concession from exposure to attack reasoning.
## Input
- **artifact**: The artifact being defended
- **attacks**: Structured attacks from debate-critic (current round)
- **previous_defenses**: Defenses from prior rounds (for consistency)
## Output
- **defenses**: List of responses (concede, rebut, or clarify per attack)
- **confidence**: Defender's confidence in artifact survival (0.0–1.0)
- **concessions**: Any points conceded as valid weaknesses
## Budget
One unit = one set of defenses for one round of attacks.
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!
