skills.rest
Kang-chen
Kang-chenCOMMUNITY
Explore all skills by this author →
GitHub

automl-optimizer

Automate hyperparameter tuning and model selection with Optuna, Hyperopt, and AutoML libraries.

1|Updated Jan 29, 2026
Search Tags:#hyperparameter tuning#model selection#experiment tracking#automl#nas#optuna#algorithm comparison
One-click install
npx skills add https://github.com/Kang-chen/cartabio-ide-config --skill automl-optimizer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: automl-optimizer
Source: https://github.com/Kang-chen/cartabio-ide-config/tree/main/skills/models/automl-optimizer
Command: npx skills add https://github.com/Kang-chen/cartabio-ide-config --skill automl-optimizer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates the process of hyperparameter tuning and model selection by exploring model and hyperparameter spaces with AutoML libraries, tracking experiments, and delivering optimal configurations with minimal manual intervention.

Core Features & Use Cases

  • Automated Hyperparameter Optimization: leverages Optuna, Hyperopt, and AutoML libraries to search broad spaces efficiently.
  • Strategy-based AutoML: supports hyperparameter optimization, algorithm selection, and neural architecture search with end-to-end experiment tracking.
  • Practical Integration: logs experiments to .specweave increments, supports living docs and reproducibility, and provides guidance for common ML workflows.

Quick Start

Run the AutoML optimizer with an increment to start a hyperparameter search and review the best model.

Frequently Asked Questions about automl-optimizer

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

FAQPage Schema
How do I automate hyperparameter tuning across different ML pipelines?▼

Automated hyperparameter tuning evaluates broad parameter spaces across ML pipelines using Optuna, Hyperopt, and AutoML libraries to deliver optimal configurations with minimal manual intervention.

What is neural architecture search and when do I need it for model selection?▼

Neural architecture search automatically discovers optimal network structures. You need it when manual architecture design becomes intractable and AutoML strategies are required to explore complex model spaces efficiently.

Can I use Optuna and Hyperopt together for algorithm comparison?▼

Yes, the AutoML strategy supports both Optuna and Hyperopt libraries simultaneously. It leverages both to search broad hyperparameter spaces and perform algorithm comparison with end-to-end experiment tracking.

What's the best way to track hyperparameter optimization experiments for reproducibility?▼

The best way to ensure reproducibility is logging experiments to SpecWeave-style increments. This approach creates living documentation to audit, share, and reproduce optimal model results across increments.

Do I need living documentation to review automated model selection results?▼

No, but living documentation provides comprehensive experiment tracking and reproducibility. It logs automated model selection increments to audit workflows and share optimal configurations across ML pipelines.

Related Skills

Explore More Data & Analytics Skills→
thinking-machines-labthinking-machines-lab
4.0k

dpo

Configure and run Direct Preference Optimization training with a model and preference dataset.

Official
Intermediate
duylinhdang1998duylinhdang1998

ml-infrastructure

Build and deploy ML training pipelines with Docker, Kubernetes, and FastAPI.

Community
Advanced
tripplen23tripplen23
1

huggingface-trackio

Logs ML training metrics via Python API for Trackio dashboards and alerts.

Community
Intermediate
seb1nseb1n
147

hyperparameter-tuning

Optimize machine learning model hyperparameters using grid search, random search, and Bayesian optimization.

Community
Advanced