What orchestration platforms does this skill support?

This skill supports Apache Airflow for enterprise workflows, Prefect for Python-native orchestration, and standard cron for simple batch processing.

How does the pipeline handle forecast quality issues?

The generator includes monitoring logic that checks metrics like sMAPE and MASE, with built-in fallback capabilities to baseline models if quality thresholds aren't met.

Is an existing configuration required?

Yes, this skill typically expects a validated experiment configuration (usually from nixtla-experiment-architect) as the blueprint for the production pipeline.

Does it handle data ingestion and storage?

Yes, the generated pipelines follow an ETL pattern (Extract, Transform, Forecast, Load) and allow you to define custom data sources and destinations.

Do I need a Nixtla API key to use the generated pipelines?

A NIXTLA_API_KEY is required if you are using TimeGPT models, but the pipelines can also run StatsForecast baselines without an API key.

Nixtla Production Pipeline Generator

Name: Nixtla Production Pipeline Generator
Author: intent-solutions-io

byintent-solutions-io

Ciencia de Datos y ML

Automates the transformation of forecasting experiments into production-ready inference pipelines using Airflow, Prefect, or cron orchestration.

Acerca de

The Nixtla Production Pipeline Generator bridges the gap between data science experimentation and enterprise-grade deployment. It streamlines the operationalization of TimeGPT and StatsForecast models by generating complete deployment artifacts, including ETL tasks, monitoring protocols, and error-handling logic. Whether you need a complex Airflow DAG with dependencies or a lightweight cron script for batch processing, this skill provides the infrastructure code necessary to move forecasting models from a notebook into a reliable production environment.

Características Principales

Multi-platform orchestration support for Airflow, Prefect, and Cron
Generation of comprehensive deployment documentation and requirements
Direct integration with Nixtla experiment configurations
0 GitHub stars
Built-in forecast monitoring with automatic fallback to baseline models
Automated ETL task generation (Extract, Transform, Forecast, Load)

Casos de Uso

Setting up automated batch inference workflows for TimeGPT models
Implementing robust model monitoring and quality checks in production pipelines
Converting a local forecasting experiment into a scheduled enterprise Airflow DAG

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add intent-solutions-io/plugins-nixtla nixtla-prod-pipeline-generator

For use in Claude.ai and ChatGPT

Download Skill

GitHub