judge-prompt
OfficialDesign 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 requiredComponents
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.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.