scomp-link

Automate machine learning workflows from data profiling to deployment.

3|Updated Feb 26, 2026

Search Tags:#automation #cli #mlops #data science #machine learning #predictive modeling

Ready to run

npx skills add https://github.com/GiacomoSaccaggi/scomp_link --skill scomp-link

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: scomp-link
Source: https://github.com/GiacomoSaccaggi/scomp_link/tree/main/skills/scomp-link
Command: npx skills add https://github.com/GiacomoSaccaggi/scomp_link --skill scomp-link

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, pandas, scikit-learn, plotly, optuna, flask, and includes references (resource) and assets (resource) components.

What problem does it solve?

This Skill solves the fragmentation of machine learning workflows by providing a unified, zero-code toolkit that handles everything from initial data profiling to production deployment.

Core Features & Use Cases

End-to-End Automation: Automates data profiling, feature engineering, model selection, training, and deployment.
Production-Ready Artifacts: Generates persistent .scomp artifacts containing models, preprocessors, and metrics for reliable versioning.
Use Case: Use this to quickly profile a dataset, train a regression model with automated hyperparameter tuning, and serve it as a REST API without writing custom boilerplate code.

Quick Start

Use the scomp-link skill to profile the dataset named train.csv and generate a summary table.

Frequently Asked Questions about scomp-link

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

FAQPage Schema

How do I automate machine learning workflows from the command line without writing boilerplate code?▼

You can automate machine learning workflows from the command line by using a zero-code toolkit that handles end-to-end pipelines, including data profiling, feature engineering, model training, and deployment.

What is the best way to train a scikit-learn model with automated hyperparameter tuning and serve it as a REST API?▼

The best way to train a scikit-learn model with automated hyperparameter tuning and serve it as a REST API is to use an end-to-end automation pipeline that generates production-ready artifacts and deploys them directly via Flask.

Do I need pandas and numpy installed to run automated data profiling and feature engineering pipelines?▼

Yes, you need pandas and numpy installed to execute automated data profiling and feature engineering pipelines, as these libraries are required dependencies for processing data and generating persistent model artifacts.

Can I version and persist my trained machine learning models and preprocessors for reliable production monitoring?▼

You can version and persist trained machine learning models and preprocessors by generating persistent .scomp artifacts that contain models, preprocessing logic, and evaluation metrics for reliable production monitoring.

How does optuna integrate with automated model selection for predictive modeling?▼

Optuna integrates with automated model selection for predictive modeling by providing automated hyperparameter tuning capabilities within the end-to-end machine learning workflow, optimizing scikit-learn models during the training pipeline.