scoring-synthesis

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

Synthesizes scores, rankings, and sensitivity into a final recommendation

  • Aggregates multi-criteria scoring data into actionable decision insights
  • Uses score matrix, rankings, and sensitivity analysis from prior steps
  • Evaluates trade-offs and stability across criteria to determine optimal choice
  • Produces structured output with recommendation, confidence, and risk factors

SKILL.md

.github/skills/scoring-synthesisView on GitHub ↗
---
name: scoring-synthesis
description: Synthesize score matrix, rankings, and sensitivity analysis into a final recommendation.
execution: subagent
prompt: ./prompt.md
input: score_matrix (object), rankings (object), sensitivity (object)
used-by: multi-criteria-scoring
---

# Scoring Synthesis

Synthesize scoring matrix, ranking results, and sensitivity analysis to produce final decision recommendations.

## Execution

Subagent receives complete scoring data, ranking results, and sensitivity analysis, produces a structured final recommendation.

## Why Subagent

Comprehensive recommendation requires weighing multiple signals and making judgments; independent execution ensures recommendation completeness and traceability.

## HARD-GATE

Final recommendation must include a clear recommended alternative, confidence assessment, key assumptions, and risk warnings; reports without conclusions are not allowed.

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.