Evaluates prompts with test cases, rubrics, expected behaviors, regressions, and comparative results.
---
name: prompt-tester
description: >-
Design, test, and iterate on AI prompts systematically using structured
evaluation criteria. Use when building AI features, optimizing agent
instructions, comparing prompt variants, or evaluating output quality
across edge cases. Trigger words: prompt engineering, prompt testing,
eval, LLM evaluation, prompt comparison, A/B test prompts, prompt
optimization, system prompt, instruction tuning.
license: Apache-2.0
compatibility: "Works with any LLM-based workflow or AI agent system"
metadata:
author: terminal-skills
version: "1.0.0"
category: data-ai
tags: ["prompt-engineering", "llm", "evaluation", "ai-agents"]
---
# Prompt Tester
## Overview
Build a systematic approach to prompt engineering. Design test cases, define evaluation rubrics, run prompt variants against edge cases, and compare results to find the best-performing prompt for your use case.
## Instructions… load the full skill through Skill Me