cortex-model

Automate end-to-end ML pipelines from data ingestion to serving endpoints.

69|8|Updated Mar 16, 2026

Search Tags:#pipeline #training #ml #machine-learning #serving #feature-engineering

Ready to run

npx skills add https://github.com/tonone-ai/tonone --skill cortex-model

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: cortex-model
Source: https://github.com/tonone-ai/tonone/tree/main/team/cortex/skills/cortex-model
Command: npx skills add https://github.com/tonone-ai/tonone --skill cortex-model

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates the end-to-end ML workflow, from data validation and feature engineering to training, evaluation, and serving.

Core Features & Use Cases

Data validation and preprocessing
Feature engineering and model training
End-to-end deployment and serving with monitoring

Quick Start

Create a minimal ML pipeline that ingests data, trains a baseline model, and deploys a serving endpoint.

Frequently Asked Questions about cortex-model

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

FAQPage Schema

How do I build an end-to-end machine learning pipeline from data ingestion to serving?▼

To build an end-to-end machine learning pipeline, you need to automate data ingestion, validation, feature engineering, model training, and deployment. This Skill creates that workflow, outputting a trained model and serving endpoint with monitoring hooks for reliability.

Can I use this pipeline for both classification and regression model training?▼

Yes, this pipeline supports model training for classification, regression, and forecasting tasks. It automates the workflow from data validation and feature engineering through evaluation, ensuring reproducibility for your specific machine learning use case.

What is the best way to automate ML deployment and serving endpoint creation?▼

The best way to automate ML deployment is to use a pipeline that handles model serialization and serving endpoint creation natively. This Skill deploys trained models directly, attaching monitoring hooks to track serving reliability and performance.

Does this pipeline handle data validation and feature engineering automatically?▼

Yes, this pipeline handles data validation and feature engineering automatically. It ingests your raw data, applies necessary preprocessing and validation checks, and engineers features before passing them to the model training phase.

How does experiment tracking work for reproducible machine learning pipelines?▼

Experiment tracking in reproducible machine learning pipelines works by logging data validation steps, feature engineering outputs, and model training metrics. This Skill satisfies experiment tracking requirements to ensure consistent evaluation and deployment reliability.

Do I need external dependencies to deploy a serving endpoint with monitoring hooks?▼

No external dependencies are required to deploy a serving endpoint with monitoring hooks. This Skill operates independently, providing model serialization and serving capabilities with built-in monitoring directly within the generated pipeline.