Skill 101

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.

legendtkl Updated 8 repo stars

File contents

legendtkl/agentic-skill-router commit 1c775bb8b1

Frequently asked questions

npx get-skill add legendtkl/skill-101