Skills
.Work. You
Rest

agentic-eval

Official

Improve AI outputs with self-critique loops.

Software Engineering#rubric#quality-assurance#feedback-loop#self-critique#evaluate#LLM-evaluation#code-refinement
Authorgithub
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill enables automated self-evaluation and iterative refinement of AI-generated outputs, reducing errors and enhancing quality through structured critique loops.

Core Features & Use Cases

  • Basic Reflection: Agents critique their own output and refine it based on feedback.
  • Evaluator-Optimizer: Separate generation and evaluation to improve reliability.
  • Code-Specific Reflection: Test-driven refinement for code and technical artifacts.
  • Use Case: Improve code, reports, and analyses by applying consistent evaluation criteria and iterative improvements.

Quick Start

Initiate a 3-iteration evaluation cycle on your task: Generate → Evaluate → Critique → Refine → Output

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: agentic-eval
Download link: https://github.com/github/awesome-copilot/archive/main.zip#agentic-eval

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.