run

Run the full AgentHub lifecycle with init, baseline, spawn, eval, and merge.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies the lifecycle of AgentHub operations by chaining initialization, baseline capture, agent spawning, evaluation, and merging into a single command.

Core Features & Use Cases

  • Lifecycle Management: Execute the full AgentHub lifecycle (init, baseline, spawn, eval, merge) with one command.
  • Customizable Parameters: Configure tasks, number of agents, evaluation commands, and metrics.
  • Agent Templates: Utilize predefined agent templates like optimizer, refactorer, test-writer, and bug-fixer.

Quick Start

Run the AgentHub lifecycle for a "Refactor auth module" task with two agents using the refactorer template.

Frequently Asked Questions about run

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

FAQPage Schema
How do I run the full AgentHub lifecycle in a single command?

You can execute the complete AgentHub lifecycle—including initialization, baseline capture, agent spawning, evaluation, and merging—by running a single one-shot command with customizable parameters for tasks and agent count.

What AgentHub agent templates are available for automated task execution?

AgentHub provides predefined agent templates including optimizer, refactorer, test-writer, and bug-fixer to streamline specific task execution within the lifecycle management workflow.

Can I configure custom evaluation commands and metrics for AgentHub agents?

Yes, AgentHub lifecycle management supports custom evaluation commands and configurable metrics, allowing you to specify the exact criteria for evaluating spawned agents during execution.

What is the best way to manage multiple agents during an evaluation lifecycle?

Managing multiple agents is handled through the lifecycle command, which supports agent spawning with parallel execution options and predefined templates to optimize the evaluation and merging process.

Does the AgentHub lifecycle command support parallel execution for spawned agents?

Yes, the AgentHub lifecycle command supports parallel execution options for spawned agents, enabling simultaneous processing during the evaluation phase to accelerate task completion.