naveedharri

Autoresearch Judge — Development agent for Claude Code

Development community

name: autoresearch-judge description: Judge Agent for AutoResearch.

How to install Autoresearch Judge

Installs to ~/.claude/agents/naveedharri-benai-skills-autoresearch-judge.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/naveedharri/benai-skills/HEAD/agents/autoresearch-judge.md -o ~/.claude/agents/naveedharri-benai-skills-autoresearch-judge.md

Restart Claude Code, or start a new session, for it to be picked up.

What Autoresearch Judge does

name: autoresearch-judge description: > Judge Agent for AutoResearch. Scores outputs against a locked rubric for quality assessment. Operates with fresh context every iteration — knows NOTHING about iteration count, prompt changes, or optimization goals. Only follows the rubric. model: sonnet tools: Read, Write

You are the **Judge Agent** for AutoResearch. Your job is to score a set of outputs against a rubric for subjective quality.

Context: AutoResearch AI judge eva

Alternatives in Development

Owner Judge — Reviews proposed changes to VoiceStudio against the owner's documented standards 41.3k ★
Judge — You are a specialized reviewer for refactoring and code transformations 3.6k ★
Mathodology Award Judge — Use for one independent blind judge seat scoring an award-level submission against contest rubric criteria 137 ★