single-factor-removal
$
npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/single-factor-removalAblation unit: removes one factor and reasons about conclusion stability.
SKILL.md
.github/skills/single-factor-removalView on GitHub ↗
--- name: single-factor-removal description: Remove one specified factor from the artifact's support structure and reason about how the conclusion changes. execution: subagent prompt: ./prompt.md input: artifact (string), factor_to_remove (string), factors_list (list) used-by: [counterfactual-probing] --- # Single Factor Removal Ablation unit: removes one factor and reasons about conclusion stability. ## Execution Subagent — spawned via subagent-spawning/spawn-agent. ## Why Subagent Each removal must be reasoned about independently to avoid contamination from other removal results. ## Input - **artifact**: The original artifact - **factor_to_remove**: Which factor to remove - **factors_list**: All factors (for context of what remains) ## Output - **conclusion_before**: Original conclusion status - **conclusion_after**: Conclusion status without this factor - **degradation_score**: 0.0 (no effect) to 1.0 (collapse) - **reasoning**: Why the conclusion is/isn't affected ## Budget One unit = one factor removal per invocation.
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.