init

Initialize AgentHub collaboration sessions with configurable task, agent count, and evaluation criteria.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/4lerman/text_evaluator --skill init-4lerman
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: init
Source: https://github.com/4lerman/text_evaluator/tree/main/.agents/skills/engineering-advanced-skills/agenthub/skills/init
Command: npx skills add https://github.com/4lerman/text_evaluator --skill init-4lerman

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the challenge of manually setting up and configuring AgentHub collaboration sessions, by automating the initialization process with task definitions, agent counts, and evaluation criteria.

Core Features & Use Cases

  • Session Initialization: Automatically creates the necessary directory structure and session ID for a new collaboration session.
  • Customizable Parameters: Allows setting the task, number of agents, and evaluation criteria directly through the command line.
  • Interactive Mode: Offers an interactive interface for collecting session parameters if no command line arguments are provided.
  • LLM Judge Mode: Enables starting a session without an evaluation command, using an AI to judge the results instead.

Quick Start

To initiate a new session, run the command: /hub:init --task "Optimize API" --agents 3 --eval "pytest bench.py" --metric p50_ms --direction lower

Frequently Asked Questions about init

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I initialize an AgentHub collaboration session for a specific task?

To initialize an AgentHub collaboration session, run the command-line interface with your desired task, agent count, and evaluation criteria to automatically generate the directory structure and session ID.

Can I set up task management evaluation criteria without providing a command-line eval string?

Yes, you can start a session without an evaluation command by enabling LLM Judge Mode, which uses an AI to judge the collaboration results instead of relying on a predefined metric.

How does interactive mode work for session initialization?

Interactive mode provides an interface to collect session parameters if no command-line arguments are provided, prompting you directly for the task, number of agents, and evaluation criteria.

What's the best way to configure multiple agents for collaborative problem-solving?

The best way to configure multiple agents is using the customizable parameters flag during session initialization, allowing you to set the exact agent count needed for your software development or research workflow.

Do I need to manually create a directory structure before starting a collaboration session?

No, you do not need to manually create a directory structure, as the session initialization process automates the setup and generates the required directories and session ID automatically.

Can I use this session initialization for data analysis workflows?

Yes, this is designed for collaborative problem-solving workflows in software development, research, and data analysis, allowing you to define specific tasks and evaluation metrics for any of these contexts.