Skill329 estrellas del repoactualizado 5d ago

aggregation-method

This skill aggregates multiple ranked ballots into a single consensus ranking using social choice methods including Schulze, Borda, Kemeny-Young, Copeland, and Condorcet. Use it when you need to combine multiple preference orderings from voters or evaluators into a definitive group ranking, ensuring the output reflects genuine consensus properties like Condorcet consistency where applicable.

Ver fuente Repositorio: de-anthropocentric-research-engine

Instalar en Claude Code

Copiar

git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/aggregation-method && cp -r /tmp/aggregation-method/skills/aggregation-method ~/.claude/skills/aggregation-method

Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

Definición

SKILL.md

# Aggregation Method

Applies a social choice aggregation method to a set of ranking ballots to produce a consensus ranking. Supports Schulze, Borda, Kemeny-Young, Copeland, and Condorcet methods.

## Execution

Runs as a subagent. Receives ballots and method specification, returns the aggregated consensus ranking.

## Why Subagent

Aggregation algorithms (especially Kemeny-Young) involve combinatorial computation and method-specific logic. Isolating this ensures correct algorithm application and clear separation from collection and interpretation.

## HARD-GATE

Output MUST produce a complete ranking of all candidates. The method field MUST match the input method. If a Condorcet winner exists, it MUST be ranked first (for Condorcet-consistent methods).

Del mismo repositorio

formated-resultSkill

Experiment-specific - summarize the DARE executor's research design into a clean research_result report, forced to write back into the spec file produced by formated-specs.

formated-specsSkill

Experiment-specific - replaces writing-specs, emits DARE's 4-layer call plan as a clean research_graph schema. Last step forces load formated-result.

injection-fidelitySkill

loss-1 judge - read a sample's full dialogue and decide whether the user simulator semantically enacted its Policy Card. check-blind.

ladder-quality-orderSkill

loss-2 judge - pairwise quality comparison across the n rungs within one topic; decide monotonicity and endpoint separation. check-blind, D1-D5 only.

abductive-hypothesis-generationSkill

Strategy: 面对异常的最佳解释推理

ablation-brainstormSkill

Remove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.

ablation-component-mappingSkill

Map system architecture to ablatable units for ablation studies

ablation-designSkill

Design ablation studies to isolate component contributions in ML systems