Imported from vierohanz/ORCHESTRATION_CONFIGURATION (.agent/skills/llm-evaluation/SKILL.md). Install upstream with npx skills add vierohanz/ORCHESTRATION_CONFIGURATION --skill llm-evaluation. Copyright stays with the author.

LLM Evaluation

Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.

Do not use this skill when

• The task is unrelated to llm evaluation
• You need a different domain or tool outside this scope

Instructions

• Clarify goals, constraints, and required inputs.
• Apply relevant best practices and validate outcomes.
• Provide actionable steps and verification.
• If detailed examples are required, open resources/implementation-playbook.md.

Use this skill when

• Measuring LLM application performance systematically
• Comparing different models or prompts
• Detecting performance regressions before deployment
• Validating improvements from prompt changes
• Building confidence in production systems
• Establishing baselines and tracking progress over time
• Debugging unexpected model behavior

Core Evaluation Types

🧠 Knowledge Modules (Fractal Skills)

1. 1. Automated Metrics

2. 2. Human Evaluation

3. 3. LLM-as-Judge

4. BLEU Score

5. ROUGE Score

6. BERTScore

7. Custom Metrics

8. Single Output Evaluation

9. Pairwise Comparison

10. Annotation Guidelines

11. Inter-Rater Agreement

12. Statistical Testing Framework

13. Regression Detection

14. Running Benchmarks