debate-critic
$
npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/debate-criticGenerates structured adversarial criticism using Toulmin model
- Analyzes artifacts to identify weaknesses for attack
- Uses Toulmin model components: claims, grounds, warrants, rebuttals
- Adjusts depth based on escalation level and attack vectors
- Returns attacks with confidence scores and escalation guidance
SKILL.md
.github/skills/debate-criticView on GitHub ↗
--- name: debate-critic description: Generates structured criticism from attack stance using Toulmin model. Produces claims, grounds, warrants, and rebuttals targeting artifact weaknesses. execution: subagent prompt: ./prompt.md input: artifact (string), escalation_level (string), attack_vectors (string) used-by: [multiagent-debate] --- # Debate Critic Generates structured adversarial criticism targeting artifact weaknesses. ## Execution Subagent — spawned via subagent-spawning/spawn-agent. ## Why Subagent Attack generation requires dedicated adversarial stance without contamination from defensive reasoning. Isolated context ensures pure opposition. ## Input - **artifact**: The artifact being debated (full text) - **escalation_level**: Current level (L1-surface, L2-structural, L3-foundational) - **attack_vectors**: Specific angles to attack (from debate-architect) ## Output - **attacks**: List of structured attacks (claim + ground + warrant + rebuttal anticipation) - **confidence**: How confident the critic is in each attack (0.0–1.0) - **escalation_suggestion**: Whether to escalate, maintain, or de-escalate ## Budget One unit = one set of attacks for one round.
More from yogsoth-ai/de-anthropocentric-research-engine
- abductive-hypothesis-generationStrategy: 面对异常的最佳解释推理
- ablation-brainstormRemove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.
- ablation-component-mappingMap system architecture to ablatable units for ablation studies
- ablation-designDesign ablation studies to isolate component contributions in ML systems
- ablation-executionRemove components one by one from a system, record the response/impact of each removal.
- abp-vulnerability-classificationClassify assumptions on 2 axes — load-bearing (how much conclusion depends on it) × vulnerable (how likely to be false). Focuses attention on High-Load × High-Vulnerable quadrant.
- abstraction-extractionExtract abstract principles from concrete domain cases. Strips domain-specific details to reveal transferable mechanisms.
- abstraction-ladderPerform bisociation at multiple abstraction levels
- abstraction-ladderingMove between concrete and abstract framings — 3 levels up (Why?) and 3 levels down (How?) to find the most productive research level.
- abstraction-to-designAbstract biological principle to design principle. Bridge from biology to engineering.