cross-examination
$
npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/cross-examinationIdentifies weaknesses in defender responses through targeted probing
- Detects inconsistencies, logical gaps, and unsupported claims in defenses
- Uses structured input from debates and artifacts for context
- Analyzes defenses independently to avoid framing bias
- Returns targeted follow-up questions and a verdict on defense validity
SKILL.md
.github/skills/cross-examinationView on GitHub ↗
--- name: cross-examination description: Probes defender responses for inconsistencies, logical gaps, and unsupported claims. Acts as follow-up interrogation after initial defense. execution: subagent prompt: ./prompt.md input: defenses (string), attacks (string), artifact (string) used-by: [multiagent-debate] --- # Cross-Examination Probes defender responses for inconsistencies and logical gaps. ## Execution Subagent — spawned via subagent-spawning/spawn-agent. ## Why Subagent Cross-examination requires fresh analytical perspective on the defense — isolated context prevents anchoring to either attack or defense framing. ## Input - **defenses**: Structured defenses from debate-defender - **attacks**: Original attacks that prompted the defenses - **artifact**: The artifact being debated (for reference) ## Output - **probes**: List of follow-up questions targeting defense weaknesses - **inconsistencies**: Contradictions found within or between defenses - **unsupported_claims**: Defense claims lacking evidence - **verdict_suggestion**: Whether defense held up under examination ## Budget One unit = one cross-examination pass per 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.