judge-prompt

Official

Design binary LLM evaluation prompts.

AuthorMiosa-osa
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Design binary pass/fail evaluation prompts for LLMs to standardize judgments of model outputs and reduce subjective variability.

Core Features & Use Cases

  • Criteria definition: define concrete, binary pass/fail criteria for outputs.
  • Rubric construction: create explicit pass/fail descriptions and edge cases.
  • Few-shot calibration: select calibration examples to stabilize judgments.
  • Bias mitigation: incorporate guardrails against common biases in evaluation.

Quick Start

Invoke the judge-prompt CLI with a specific task to generate a ready-to-deploy evaluation prompt for your pipeline.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: judge-prompt
Download link: https://github.com/Miosa-osa/canopy/archive/main.zip#judge-prompt

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.