Skip to content
appsgit

Agentic Eval

Agentic Eval is an agent skill (a SKILL.md file) from github/awesome-copilot. Patterns and techniques for evaluating and improving AI agent outputs. It works with Claude Code and GitHub Copilot and has 39,749 GitHub stars across a repository of 7 listed skills.

github.com/github/awesome-copilot/skills/agentic-eval (opens in a new tab)

View on GitHub (opens in a new tab)

Add this skill

Claude

Claude Code loads skills from ~/.claude/skills/ (all projects) or .claude/skills/ (one project):

git clone --depth 1 https://github.com/github/awesome-copilot.git
cp -r awesome-copilot/skills/agentic-eval ~/.claude/skills/agentic-eval   # personal, or .claude/skills in a project

In the Claude apps, zip the agentic-eval folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).

ChatGPT / Codex

Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:

git clone --depth 1 https://github.com/github/awesome-copilot.git
cp -r awesome-copilot/skills/agentic-eval .agents/skills/agentic-eval   # repo; ~/.agents/skills for all projects

Standalone skills also load in the ChatGPT desktop app.

Cursor

Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:

git clone --depth 1 https://github.com/github/awesome-copilot.git
cp -r awesome-copilot/skills/agentic-eval .cursor/skills/agentic-eval   # project; ~/.cursor/skills for all projects

Source (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)

What this skill does

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) - Measuring and improving agent response quality Patterns for self-improvement through iterative…

More skills in github/awesome-copilot

7 skills are listed from this repository.

Similar skills

More testing & qa skills

All Testing & QA

FAQ

Agentic Eval FAQ

Still curious? Email info@appsgit.com.

What is the Agentic Eval skill?

Agentic Eval is an agent skill (a SKILL.md file) from github/awesome-copilot. Patterns and techniques for evaluating and improving AI agent outputs. It works with Claude Code and GitHub Copilot and has 39,749 GitHub stars across a repository of 7 listed skills. Its SKILL.md lives at github.com/github/awesome-copilot/skills/agentic-eval.

How do I install the Agentic Eval skill?

Copy the agentic-eval folder (the one containing SKILL.md) into ~/.claude/skills/ for Claude Code, .agents/skills/ for Codex or .cursor/skills/ for Cursor. The agent picks it up automatically when a task matches its description.

Is the Agentic Eval skill free?

Yes. The repository is open source under the MIT license.

Is Agentic Eval maintained?

The repository's most recent commit was on Oct 7, 2026. appsgit only lists skills from repositories with a commit in the last six months.