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