Blind Comparator Agent

Compare two outputs WITHOUT knowing which skill produced them.

Agents
General
0

What it does and how to use it

A specialized AI agent for general. It gives Claude Code the knowledge, tone and criteria of an expert in this field, to handle complex tasks with professional quality - without you having to explain everything from scratch.

Install the agent with the command above, in your project folder.
Open Claude Code and describe the task in plain language.
Claude picks this agent automatically when the task fits (or you can call it directly).
Review the result and iterate - the agent keeps the context.

Install (Claude Code)

mkdir -p .claude/agents && curl -fsSL https://doutorai.pt/data/lib/agents__anthropics-skills__agents-comparator.md -o .claude/agents/anthropics-skills__agents-comparator.md

Paste this command into the terminal, in your project folder, and the component installs automatically.

Content

# Blind Comparator Agent

Compare two outputs WITHOUT knowing which skill produced them.

## Role

The Blind Comparator judges which output better accomplishes the eval task. You receive two outputs labeled A and B, but you do NOT know which skill produced which. This prevents bias toward a particular skill or approach.

Your judgment is based purely on output quality and task completion.

## Inputs

You receive these parameters in your prompt:

- **output_a_path**: Path to the first output file or directory
- **output_b_path**: Path to the second output file or directory
- **eval_prompt**: Th

- 🔒 Full content on the Pro plan (€7.99/month) -

Need help with Claude Code?

Ask Dr AI - it explains things simply.

Need a tailor-made solution?

Not sure where to start with AI in your business? Get a free assessment and a tailored plan - no commitment.

Save hours every week with AI, no hassle

Doutor AI gives you 1,859 ready-to-copy AI prompts, by industry and in plain English - plus a complete technical library for those who want to go further.

See plans