Automate end-to-end ML workflows from raw data to deployed models.
npx skills add https://github.com/k1lgor/virtual-company --skill ml-engineer-k1lgor
Please help me install this Agent Skill. Skill: ml-engineer Source: https://github.com/k1lgor/virtual-company/tree/main/skills/18-ml-engineer Command: npx skills add https://github.com/k1lgor/virtual-company --skill ml-engineer-k1lgor
This skill helps teams design, train, evaluate, and deploy machine learning models from raw data, reducing manual integration and setup.
Provide a dataset and ask me to build, train, evaluate, and deploy a full ML model pipeline.
High-intent search queries and answers about installing and using this skill.
Yes, you can train and deploy machine learning models using scikit-learn, XGBoost, and PyTorch. It supports model selection, training, and cross-validation across tabular, text, and image data, exporting standardized pipelines and evaluation reports.
It supports data preprocessing and feature engineering for structured, text, and image data. This prepares raw inputs for model training and evaluation, outputting standardized pipelines and evaluation reports for seamless deployment.
Provide a dataset to automate the ML workflow from raw data to deployed models. It handles data preprocessing, model training, evaluation, and deployment, outputting standardized artifacts like models and evaluation reports.
Yes, it supports model deployment for tabular, text, and image data. The workflow includes seamless export of models and pipelines with reproducible results, ensuring standardized artifacts for production use.
amychina12Standardize raw academic paper data into analysis-ready datasets with Python codebooks.
grasbergCoordinate ML model lifecycles from notebook to production deployment.
roeimed0Integrates ML workflows for rRNA sequence classification, tree consensus, and generative tree synthesis using Python libraries.
xjtulycBuild scikit-learn pipelines with nested cross-validation and FLAML AutoML.
