Skip to content
Skill

Eval driven dev

Improve AI application with evaluation-driven development

Install
Scripts
shell, Python
Platforms
Claude Code, Codex, Cursor
GitHub stars
41.3K
Last commit
1 day ago
License
MIT
Listing updated
today

When your agent uses it

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.

From the skill's SKILL.md. Your agent reads this description to decide when to load the skill.

What it can access

From a static check of its 19 files (165 KB) on GitHub on 17 November 2026. Nothing was run. Read the files before you install a skill: it can tell your agent to run anything its tools allow.

Install

Copy the skill folder to ~/.claude/skills/eval-driven-dev to use it in all your projects:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/github/awesome-copilot.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/eval-driven-dev &&
cp -R "$tmp/skills/eval-driven-dev" ~/.claude/skills/eval-driven-dev &&
rm -rf "$tmp"

For one project only, put the folder in .claude/skills/eval-driven-dev inside it instead.

Claude Code docs on skills

Copy the skill folder to ~/.agents/skills/eval-driven-dev to use it in every repository:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/github/awesome-copilot.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/eval-driven-dev &&
cp -R "$tmp/skills/eval-driven-dev" ~/.agents/skills/eval-driven-dev &&
rm -rf "$tmp"

For one repository only, put the folder in .agents/skills/eval-driven-dev inside it instead.

Codex docs on skills

Copy the skill folder to ~/.cursor/skills/eval-driven-dev to use it in every project:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/github/awesome-copilot.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/eval-driven-dev &&
cp -R "$tmp/skills/eval-driven-dev" ~/.cursor/skills/eval-driven-dev &&
rm -rf "$tmp"

For one project only, put the folder in .cursor/skills/eval-driven-dev inside it instead.

Cursor docs on skills

Run in a terminal (add --scope workspace to install it for the current workspace only):

gemini skills install https://github.com/github/awesome-copilot.git --path skills/eval-driven-dev

Or copy the folder to ~/.gemini/skills/eval-driven-dev yourself.

Gemini CLI docs on skills

For GitHub Copilot in VS Code, copy the skill folder to ~/.copilot/skills/eval-driven-dev:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/github/awesome-copilot.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/eval-driven-dev &&
cp -R "$tmp/skills/eval-driven-dev" ~/.copilot/skills/eval-driven-dev &&
rm -rf "$tmp"

For one project only, put the folder in .github/skills/eval-driven-dev inside it instead.

VS Code docs on skills

Get the folder:

git clone --depth 1 https://github.com/github/awesome-copilot.git

Then copy awesome-copilot/skills/eval-driven-dev into your agent's skills folder as eval-driven-dev. Agents that support SKILL.md read one folder per skill.

The SKILL.md format

Eval driven dev FAQ

How do I install Eval driven dev in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/eval-driven-dev to use it in all your projects, or to .claude/skills/eval-driven-dev in one project.

Does Eval driven dev run scripts?

Yes. It runs shell and Python scripts. No network calls were found in its scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

Which AI agents can use Eval driven dev?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

More from github/awesome-copilot

  1. Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.

    • Open source
    • 41.3K GitHub stars
  2. Review pull requests for repository fit, meaningful value, trustworthy provenance, differentiation, and maintainability in awesome-copilot.

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  3. Create or register a canvas extension in the awesome-copilot repository

    • Open source
    • 41.3K GitHub stars
  4. Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase

    • Open source
    • 41.3K GitHub stars
  5. Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html

    • Open source
    • 41.3K GitHub stars
    • Developer tools