Agents-eval

qte77/Agents-eval

A Multi-Agent System (MAS) evaluation framework using PydanticAI that generates and evaluates scientific paper reviews through a three-tiered assessment approach: traditional metrics, LLM-as-a-Judge, and graph-based complexity analysis.

2 stars

1 forks

Python

1 views

View on GitHub Add to Favorites

Installation

Option 1: Use slash command in Claude Code

/install-skill https://github.com/qte77/Agents-eval

Option 2: Clone to skills directory

# Global (all projects)

git clone https://github.com/qte77/Agents-eval ~/.claude/skills/Agents-eval

# Project-specific

git clone https://github.com/qte77/Agents-eval .claude/skills/Agents-eval

Add MCP server to .cursor/mcp.json:

{
  "mcpServers": {
    "skillz": {
      "command": "npx",
      "args": ["-y", "skillz-mcp", "https://github.com/qte77/Agents-eval"]
    }
  }
}

Restart Cursor after adding the configuration.

Option 1: Use Gemini CLI command

gemini extensions install https://github.com/qte77/Agents-eval

Option 2: Clone to extensions directory

git clone https://github.com/qte77/Agents-eval ~/.gemini/extensions/Agents-eval

Topics

Related Skills

skill-writer

Tensors and Dynamic neural networks in Python with strong GPU acceleration

xlsx

Public repository for Agent Skills

agno

The programming language for agentic software. Build, run, and manage multi-agent systems at scale.

youtube-downloader

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows