Directory / Awesome Copilot skills (GitHub) / eval-driven-dev

eval-driven-dev

Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate application runs, analyze results, and produce a concrete action plan for improvements. ALWAYS USE THIS SKILL when the user asks to set up QA, add tests, add evals, evaluate, benchmark, fix wrong behaviors, improve quality, or do quality assurance for any Python project that calls an LLM model.
Description from the SKILL.md front matter.

Install

GitHub CLI v2.90+ (Copilot by default)

gh skill install github/awesome-copilot eval-driven-dev

For Claude Code

gh skill install github/awesome-copilot eval-driven-dev --agent claude-code

For Codex

gh skill install github/awesome-copilot eval-driven-dev --agent codex

Commands follow each host's documentation (GitHub Copilot, plus Claude Code, Codex, Cursor via gh skill docs). gh skill needs GitHub CLI 2.90 or later and is in public preview.

Listed from GitHub + community contributors's catalog, not reviewed by us. Read the source before installing.

Catalog: Awesome Copilot skills (GitHub)
Author: Not stated in the source
Source code: github/awesome-copilot
License: MIT
Repository stars: 40,178 for github/awesome-copilot (the whole catalog repo)
Version: 0.8.4
Added to catalog: Not tracked for this source
Last change: 2026-10-16 (last push to the repo)

What it contains

Skills: 1

Similar in Software development

acquire-codebase-knowledge (Awesome Copilot skill)
acreadiness-assess (Awesome Copilot skill)
acreadiness-generate-instructions (Awesome Copilot skill)
adobe-illustrator-scripting (Awesome Copilot skill)
agentic-eval (Awesome Copilot skill)
ai-ready (Awesome Copilot skill)