Agentic Eval

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when implementing self-critique and reflection loops, building evaluator-optimizer pipelines for quality-critical generation, creating test-driven code refinement workflows, designing rubric-based or LLM-as-judge evaluation systems, adding iterative improvement to agent outputs (code, reports, analysis), and measuring agent response quality.

majiayu000 Updated 735 repo stars

File contents

majiayu000/claude-skill-registry-data commit 44e3d3bebd

Frequently asked questions

npx get-skill add majiayu000/agentic-eval-3