researcher-evaluation

Official

Rigorous GenAI agent evaluation with G-Eval.

AuthorVibeTechnologies
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Evaluates GenAI agents using the G-Eval methodology to produce structured performance reports.

Core Features & Use Cases

  • Provides a standardized Required Output Format for evaluating multiple frameworks (AutoGen, CrewAI, OpenHands)
  • Includes a comprehensive methodology (G-Eval) that scores accuracy, reasoning, and actionability across tasks
  • Offers a CLI workflow to run benchmarks and compare frameworks, with clear evaluation dimensions and a summary of results

Quick Start

Run the evaluation workflow on a sample task using the G-Eval methodology to compare agent outputs.

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: researcher-evaluation
Download link: https://github.com/VibeTechnologies/VibeTeam/archive/main.zip#researcher-evaluation

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.