comparison-executor

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

Executes pairwise comparisons to determine a winner with confidence and reasoning

  • Solves the problem of comparing two candidates objectively
  • Relies on a structured prompt and evaluation context provided by the agent
  • Analyzes specific attributes of both candidates to form a judgment
  • Returns a JSON result with winner, confidence score, and reasoning
SKILL.md
.github/skills/comparison-executorView on GitHub ↗
---
name: comparison-executor
description: Execute a pairwise comparison between two candidates, producing a judgment with winner, confidence, and reasoning.
execution: subagent
prompt: ./prompt.md
input: pair(array), context(object)
used-by: pairwise-ranking
---

# Comparison Executor

Executes a single pairwise comparison between two candidates. Produces a structured judgment indicating the winner, confidence level, and detailed reasoning supporting the decision.

## Execution

Runs as a subagent. Receives a pair of candidates and evaluation context, returns a judgment.

## Why Subagent

Each comparison requires focused deliberation on the specific pair without being influenced by prior ranking expectations. Isolation prevents anchoring bias from the current leaderboard.

## HARD-GATE

Output MUST declare exactly one winner from the pair (no ties unless context explicitly permits ties). Confidence MUST be a value in [0.5, 1.0]. Reasoning MUST reference specific attributes of both candidates.
More from yogsoth-ai/de-anthropocentric-research-engine