agentic-eval — Skills — getagentictools

What it does

Quality-critical generation: Code, reports, analysis requiring high accuracy

Tasks with clear evaluation criteria: Defined success metrics exist

Content requiring specific standards: Style guides, compliance, formatting

[ ] Define evaluation criteria/rubric

[ ] Set score threshold for "good enough"

[ ] Configure max iterations (default: 3)

[ ] Implement generate() function

Iterative evaluation and refinement patterns for improving AI agent outputs through self-critique loops.

Source

Repository: https://github.com/github/awesome-copilot

agentic-eval FAQ

What does the agentic-eval skill do?

| 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 Quality-critical generation: Code, reports, analysis requiring high accuracy Tasks with clear evaluation criteria: Defined success metrics exist

How do I install agentic-eval?

Run: npx -y skills add https://github.com/github/awesome-copilot --skill agentic-eval --agent claude-code — the source lives at github.com/github/awesome-copilot.

Maintain agentic-eval?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[![agentic-eval on getagentictools](https://getagentictools.com/badge/skills/github-awesome-copilot-agentic-eval.svg)](https://getagentictools.com/skills/github-awesome-copilot-agentic-eval?ref=badge)

npx agentictools info skills/github-awesome-copilot-agentic-eval

The second line is the CLI lookup for this page — handy in READMEs and docs.