run

Orchestrate the full AgentHub lifecycle in a single command.

Updated Apr 9, 2026
One-click install
npx skills add https://github.com/Patasse97/claude-skills --skill run-patasse97
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: run
Source: https://github.com/Patasse97/claude-skills/tree/main/engineering/agenthub/skills/run
Command: npx skills add https://github.com/Patasse97/claude-skills --skill run-patasse97

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill orchestrates the full AgentHub lifecycle in a single command, reducing manual orchestration and enabling reproducible multi-agent experiments.

Core Features & Use Cases

  • Orchestrates initialization, baseline capture, agent spawning, evaluation, and merge in one streamlined flow.
  • Supports configurable task parameters, agent counts, evaluation commands, metrics, and optional templates.
  • Ideal for end-to-end experiments, rapid prototyping, and production-grade agent workflows.

Quick Start

Invoke the run skill with a task description and agent count to execute the complete lifecycle in one command.

Frequently Asked Questions about run

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

FAQPage Schema
How do I automate the full multi-agent lifecycle in a single command?

To automate the multi-agent lifecycle, use this skill to orchestrate initialization, baseline capture, agent spawning, evaluation, and merge in one streamlined flow. It coordinates heterogeneous tasks with configurable agents across parallel runs.

What is multi-agent orchestration and how does it streamline experimentation?

Multi-agent orchestration coordinates initialization, baseline capture, spawning, evaluation, and merging into a single command. It streamlines reproducible multi-agent experiments by automating manual workflows and ensuring safe merge processes.

Can I configure agent counts and evaluation metrics for parallel runs?

Yes, you can configure task parameters, agent counts, evaluation commands, and metrics for parallel runs. The skill supports optional templates and applies these configurations across heterogeneous tasks to rank results.

Do I need Python-based tooling and agent templates to run this lifecycle?

Yes, you need Python-based tooling and the agent templates to execute this lifecycle. The skill requires these dependencies to ensure proper baseline capture, result ranking, and safe merge workflows during multi-agent orchestration.

What is the best way to manage reproducible multi-agent experiments end-to-end?

The best way to manage reproducible multi-agent experiments is orchestrating the full lifecycle in a single command. This skill handles initialization through merging, ensuring baseline capture, result ranking, and safe merge workflows for rapid prototyping.