DeepEval Testing

Skill for pytest-style LLM evaluation with DeepEval.

Overview

DeepEval provides:

• pytest-compatible LLM tests
• Built-in metrics (faithfulness, relevance, toxicity)
• Custom metric creation
• Async test execution

Use When

This skill is automatically invoked when:

• Creating pytest-style LLM tests
• Evaluating RAG quality
• Measuring faithfulness/relevance
• Building custom metrics

Available Scripts

Available Templates

Built-in Metrics

• AnswerRelevancyMetric
• FaithfulnessMetric
• ContextualRelevancyMetric
• HallucinationMetric
• ToxicityMetric
• BiasMetric