Skill329 repo starsupdated 5d ago

ballot-collection

Ballot Collection gathers independent ranking evaluations of candidates from multiple specified perspectives or judges, with each evaluation generated separately to prevent bias from other judges' outputs. Use this skill when you need authentic comparative rankings across different viewpoints, such as evaluating candidates through diverse criteria, stakeholder perspectives, or evaluation frameworks where independence between raters is essential.

View source Repository: de-anthropocentric-research-engine

Install in Claude Code

Copy

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

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

# Ballot Collection

Collects independent ranking ballots from multiple judges or evaluation perspectives. Each judge produces a complete or partial ranking of the candidates without seeing other judges' rankings.

## Execution

Runs as a subagent. Receives candidates and perspective definitions, returns structured ballots.

## Why Subagent

Each ballot must be generated independently to prevent anchoring. The subagent evaluates from a single perspective without access to other judges' outputs, ensuring genuine independence.

## HARD-GATE

Output MUST contain one ballot per perspective. Each ballot MUST rank all candidates (complete ranking) or explicitly mark unranked candidates. No two ballots may be identical unless perspectives are genuinely indistinguishable.