init

Name: init
Availability: InStock
Author: veloxia-agency

Initialize an AgentHub session directory with configuration and optional baseline.

Updated Apr 24, 2026

Search Tags:#collaboration #parallel agents #evaluation workflow #agenthub #session initialization #baseline capture

Ready to run

npx skills add https://github.com/Veloxia-agency/VELOXIA-WEB --skill init-veloxia-agency

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: init
Source: https://github.com/Veloxia-agency/VELOXIA-WEB/tree/main/.claude/skills/engineering/agenthub/skills/init
Command: npx skills add https://github.com/Veloxia-agency/VELOXIA-WEB --skill init-veloxia-agency

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It removes the friction of starting a coordinated AgentHub run by setting up a shared session, capturing the task context, and preparing the workflow for multiple agents.

Core Features & Use Cases

Session Setup: Creates the AgentHub session structure, generates a session ID, and stores the initial configuration.
Flexible Run Modes: Supports both interactive setup and argument-driven initialization for task execution or research workflows.
Evaluation Support: Accepts an optional eval command, metric name, and direction so performance-focused sessions can capture a baseline automatically.
Use Case: Use it when you want to compare several agent approaches to the same refactor, optimization, or content task from a single starting point.

Quick Start

Ask the assistant to initialize a new AgentHub session for your task, specifying the task, number of agents, optional evaluation command, metric direction, and base branch.

Frequently Asked Questions about init

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

FAQPage Schema

How do I initialize a multi-agent collaboration session for a shared task?▼

Initializing a multi-agent collaboration session involves creating an AgentHub session directory, generating a unique session ID, and storing the initial task configuration to coordinate multiple agents around a shared task.

What is an AgentHub session and when do I need it?▼

An AgentHub session is a shared workspace for coordinating multiple agents around a single task. You need it when running refactoring, research, or evaluation workflows that require parallel agent approaches.

Can I capture a performance baseline when setting up a parallel agent workflow?▼

Yes, you can capture a baseline during setup by providing an optional eval command, metric name, and direction. This allows performance-focused sessions to automatically record baseline metrics for comparing parallel agent approaches.

Does AgentHub session initialization support both interactive and argument-driven workflows?▼

Yes, AgentHub session initialization supports both interactive setup and argument-driven initialization. This allows you to launch task execution or research workflows using either guided prompts or direct configuration arguments.

How do I compare several agent approaches to the same refactor from one starting point?▼

You compare agent approaches by initializing a single AgentHub session with your task and agent count. The session captures the shared task context and optional baseline, enabling multiple agents to work from one starting point.

What configuration values do I need to start an evaluation-driven agent run?▼

To start an evaluation-driven agent run, you specify the task, number of agents, optional eval command, metric direction, and base branch. The initialization process records these configuration values to prepare the parallel agent workflow.