Copilot Eval-Driven Dev
SkillAdd evals to a Python LLM app: define criteria, build a golden dataset, score runs and get a fix-it plan.
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 Copilot Eval-Driven Dev
From GitHub's awesome-copilot repo, built around the open-source pixie-qa tool. Your agent instruments the app, collects runs, evaluates them against criteria you agree on, and turns the results into concrete next steps.
For anyone whose LLM feature works on the demo prompt and nobody knows about the rest.
No reviews yet
Used it? Write the first review.