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)…
Install
npx skills add github/awesome-copilot --skill agentic-evalnpx skills add github/awesome-copilot --skill agentic-eval -a claude-code -gnpx skills add github/awesome-copilot --skill agentic-eval -a codex -ggemini skills install https://github.com/github/awesome-copilot.git --path skills/agentic-evalgh skill install github/awesome-copilot agentic-evalgit clone --depth 1 https://github.com/github/awesome-copilot /tmp/github__awesome-copilot
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/github__awesome-copilot/skills/agentic-eval ~/.claude/skills/agentic-eval # Claude Code
cp -R /tmp/github__awesome-copilot/skills/agentic-eval ~/.agents/skills/agentic-eval # Codex, Cursor, Gemini CLI, Copilot, OpenCode