flip-point-detection

$npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/flip-point-detection

Detects minimal change to flip a conclusion along a specified dimension

  • Identifies smallest perturbation that reverses a logical conclusion
  • Uses binary search within isolated subagent context
  • Iteratively tests graduated changes along the specified dimension
  • Returns flip-point, distance, confidence, and search steps in structured output

SKILL.md

.github/skills/flip-point-detectionView on GitHub ↗
---
name: flip-point-detection
description: Find the minimal change magnitude along a dimension that causes the conclusion to flip from true to false.
execution: subagent
prompt: ./prompt.md
input: artifact (string), dimension (string), conclusion (string)
used-by: [counterfactual-probing]
---

# Flip-Point Detection

Binary search for the minimal perturbation that reverses the conclusion.

## Execution

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

## Why Subagent

Flip-point detection requires iterative reasoning about graduated changes, best done in isolated context.

## Input

- **artifact**: The original artifact
- **dimension**: The dimension to perturb along
- **conclusion**: The conclusion being tested

## Output

- **flip_point**: The minimal change that flips the conclusion
- **distance**: How far from actuality the flip-point is (0.0–1.0)
- **confidence**: Confidence in the flip-point location
- **search_path**: Steps taken to find the flip-point

## Budget

One unit = one binary search per dimension.

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.