ml-new

Coordinates specialists across a 14-cycle ML pipeline from discovery to sunset.

Updated Jun 21, 2026
One-click install
npx skills add https://github.com/infantesromeroadrian/arca-agent --skill ml-new
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ml-new
Source: https://github.com/infantesromeroadrian/arca-agent/tree/main/template/skills/ml-new
Command: npx skills add https://github.com/infantesromeroadrian/arca-agent --skill ml-new

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill simplifies the process of initiating a complete 14-cycle Machine Learning pipeline, ensuring every step from Discovery to Sunset is executed efficiently.

Core Features & Use Cases

  • End-to-End Pipeline: Manages all stages of an ML project, from initial discovery to sunset, with 14 distinct cycles.
  • Specialist Collaboration: Coordinates input from various specialists across different domains such as data, ML fundamentals, architecture, etc.
  • User-Friendly Activation: Triggered with a simple invocation phrase, making the ML pipeline initiation straightforward for users.

Quick Start

Initiate a new Machine Learning project with 'start a new ML project for $argument' using the /ml-new command.

Frequently Asked Questions about ml-new

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

FAQPage Schema
How do I start a machine learning pipeline for a new project?

To start a machine learning pipeline, use the /ml-new command with the invocation phrase to trigger a comprehensive 14-cycle lifecycle workflow covering discovery through sunset.

What is a 14-cycle machine learning pipeline?

A 14-cycle machine learning pipeline is a structured project lifecycle managing sequential stages from initial discovery and data preparation to final deployment and sunset procedures.

Can I coordinate specialist collaboration for data processing within an ML pipeline?

Yes, the pipeline orchestrates specialist collaboration by coordinating input from diverse domain experts across data processing, architecture, and ML fundamentals throughout the project.

Does this ML pipeline management approach handle feature engineering and testing?

Yes, the pipeline explicitly includes cycles for feature engineering, design, development, testing, and deployment alongside rigorous quality control and robust documentation requirements.

What is the best way to manage end-to-end ML project lifecycle planning?

The best way to manage an end-to-end ML project lifecycle is triggering a structured 14-cycle pipeline that enforces planning, data preparation, and sunset procedures across specialists.

Do I need specific dependencies to run this machine learning pipeline workflow?

No specific dependencies are required to run this machine learning pipeline workflow, as it operates independently using provided scripts and reference components for execution.