normalization

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

Normalize score matrix values to make them comparable across criteria

  • Identifies and normalizes raw scoring data from various sources.
  • Deploys normalization methods such as min-max scaling, z-score standardization, or others provided by external APIs.
  • Automatically adjusts scores within a [0, 1] range based on specified method to ensure comparability across different criteria.
  • Outputs the normalized score matrix for further analysis or use in decision-making processes.

SKILL.md

.github/skills/normalizationView on GitHub ↗
---
name: normalization
description: Normalize a score matrix using a specified method to make scores comparable across criteria.
execution: subagent
prompt: ./prompt.md
input: score_matrix (object), method (string)
used-by: multi-criteria-scoring
---

# Normalization

Normalize the scoring matrix to make scores with different units and scales comparable across criteria.

## Execution

Subagent receives the raw scoring matrix and normalization method, outputs the normalized matrix.

## Why Subagent

Normalization involves mathematical transformations and direction handling; independent verification of transformation correctness is needed to avoid direction errors causing rank reversals.

## HARD-GATE

All normalized values must be in the [0, 1] range, with max-direction criteria having optimal value of 1, and min-direction criteria having optimal value of 1 (after inversion).

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.