Generate end-to-end machine learning workflows from data ingestion to deployment.
npx skills add https://github.com/mikeparcewski/wicked-garden --skill ml-mikeparcewski
Please help me install this Agent Skill. Skill: ml Source: https://github.com/mikeparcewski/wicked-garden/tree/main/skills/data/ml Command: npx skills add https://github.com/mikeparcewski/wicked-garden --skill ml-mikeparcewski
This skill provides a structured workflow to guide machine learning model development, evaluation, and deployment, helping teams align architecture review, training pipeline design, feature engineering, and production readiness.
Provide an end-to-end ML workflow by asking to review a model architecture and generate a training pipeline plan for a given dataset.
High-intent search queries and answers about installing and using this skill.
To design a machine learning training pipeline, you define data flows, preprocessing steps, model training, and evaluation processes. This approach ensures reproducible workflows that guide development from data ingestion through to model deployment.
An ML model architecture review assesses model choice, data quality, evaluation strategy, and deployment readiness. This review ensures the selected architecture aligns with the dataset and production requirements before building the training pipeline.
Planning production deployment for a machine learning model involves establishing serving options, monitoring protocols, and rollback plans. These deployment guardrails ensure robust model serving and mitigate risks in the production environment.
Yes, you can generate an end-to-end ML workflow for datasets of varying sizes and domains. The workflow guides architecture review, feature engineering, training pipeline design, and deployment planning across diverse data inputs.
Feature engineering fits into the machine learning development workflow during training pipeline design, working alongside data preprocessing and model training. It helps shape data flows to improve model evaluation and deployment readiness.
lrbjkAssess Unity projects for version, render pipeline, packages, asmdefs, and folder structure.
KentoShimizuDetect data drift, concept drift, and quality degradation in production ML pipelines.
h4vzzTrain machine learning models end-to-end across PyTorch, TensorFlow, and scikit-learn.
snoodleboot-ioExplain hyperparameter tuning techniques including grid search, random search, Bayesian optimization, and reinforcement learning.
