devils-advocacy

$npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/devils-advocacy

Constructs a strong counter-argument against a given position

  • Identifies and analyzes the core assumptions of the opposing position.
  • Deploys external tools to gather relevant evidence and context for analysis.
  • Uses reasoning and argumentation techniques to construct a robust counter-argument.
  • Delivers the constructed counter-argument in a clear, structured format.

SKILL.md

.github/skills/devils-advocacyView on GitHub ↗
---
name: devils-advocacy
description: Construct the strongest possible counter-argument against a position, steelmanning the opposition before attacking.
execution: subagent
prompt: ./prompt.md
input: position (string), context (string)
used-by: [red-teaming]
---

# Devil's Advocacy

Constructs the strongest possible case against a given position or assumption.

## Execution

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

## Why Subagent

Devil's advocacy requires full commitment to the opposing position. The agent must genuinely argue against the position without hedging or pulling punches.

## Input

- **position**: The position or assumption to argue against
- **context**: Surrounding context (artifact, domain, prior findings)

## Output

- **counter_argument**: The strongest case against the position
- **evidence**: Supporting evidence for the counter-argument
- **confidence**: How strong the counter-argument actually is (0.0-1.0)
- **fatal_if_true**: Whether the counter-argument would be fatal to the artifact

More from yogsoth-ai/de-anthropocentric-research-engine

SkillDescription
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.