Skills
.Work. You
Rest

prompt-evaluator

Community

Score prompts and generate optimized rewrites.

Software Engineering#LLM#rubric#prompt#rewrite#evaluate#A/B#batch-evaluation
Authorviliawang-pm
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Systematically evaluate LLM prompts across multiple quality dimensions, produce quantitative scores, and generate optimized rewrites.

Core Features & Use Cases

  • Multi-dimension rubric: Evaluates prompts on 8 dimensions (Clarity, Specificity, Completeness, Conciseness, Structure, Grounding, Safety, Robustness).
  • Scores + rewrites: Produces a numeric rubric plus actionable rewrite suggestions to improve prompts.
  • Modes: Supports Single Prompt Evaluation, A/B Comparison, and Batch Evaluation workflows.

Quick Start

Provide a single prompt text to evaluate and receive a scored rubric with actionable rewrite suggestions.

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: prompt-evaluator
Download link: https://github.com/viliawang-pm/ai-engineering-toolkit/archive/main.zip#prompt-evaluator

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.