ranking-synthesis

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

Generates final ranking with confidence intervals and consistency status

  • Solves the problem of presenting a verified, ranked list of candidates
  • Depends on converged ratings and consistency report inputs
  • Computes confidence intervals and checks for ranking consistency
  • Returns a structured ranking artifact with metadata and quality indicators

SKILL.md

.github/skills/ranking-synthesisView on GitHub ↗
---
name: ranking-synthesis
description: Produce the final ranking artifact from converged ratings and consistency report.
execution: subagent
prompt: ./prompt.md
input: ratings(object), consistency_report(object)
used-by: pairwise-ranking
---

# Ranking Synthesis

Produces the final, presentation-ready ranking from converged ratings and consistency verification. Combines quantitative scores with confidence intervals, method metadata, and quality indicators into the deliverable artifact.

## Execution

Runs as a subagent. Receives final ratings and consistency report, returns the formatted ranking artifact.

## Why Subagent

Synthesis requires formatting decisions, confidence interval computation, and quality narrative generation that benefit from focused attention without orchestration overhead.

## HARD-GATE

Output MUST rank ALL candidates. Output MUST include confidence intervals. Output MUST reference the consistency status. No candidate may be omitted from the final ranking.

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.