Agentic Eval
- by github
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) - Measuring and improving agent response quality
npx skills add 'github/awesome-copilot' --skill 'agentic-eval' -a claude-code -yInstalls into .claude/skills/agentic-eval in this project. Add -g to install it for every project, in ~/.claude/skills/agentic-eval.
SKILL.md
Read the source documentation for full instructions.
