Agentic Eval (Awesome Copilot)
SkillPatterns for agents that grade and improve their own output: reflection loops, rubrics and LLM-as-judge.
by GitHub Listed Jun 11, 2025
Clone or download it from github.com, then drop the folder into ~/.claude/skills/ (Claude Code) or your agent's skills directory.
Product badge
Share this product's name and rating in your README or on your website.
Updates may be delayed by image caching.
About Agentic Eval (Awesome Copilot)
Skill from GitHub's Awesome Copilot collection on evaluating agent work. It lays out generate, evaluate, critique and refine loops, evaluator-optimizer pipelines, test-driven code refinement, and rubric or LLM-as-judge scoring.
Good for: adding a quality gate to an agent that writes code, reports or analysis, instead of trusting the first draft.
No reviews yet
Used it? Write the first review.