skills.rest
wyattowalsh
wyattowalshCOMMUNITY
Explore all skills by this author →
Website𝕏@wyattowalshGitHub

data-wizard

Analyze data and guide machine learning workflows across EDA, modeling, and MLOps.

4|1|Updated Jan 26, 2026
Search Tags:#mlops#machine learning#feature engineering#data analysis#model selection#eda
One-click install
npx skills add https://github.com/wyattowalsh/agents --skill data-wizard-wyattowalsh
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-wizard
Source: https://github.com/wyattowalsh/agents/tree/main/skills/data-wizard
Command: npx skills add https://github.com/wyattowalsh/agents --skill data-wizard-wyattowalsh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, scipy, numpy, scikit-learn, statsmodels, lightgbm, xgboost, catboost, interpret, category_encoders, hdbscan, prophet, pytorch-forecasting, sentence-transformers, faiss-cpu, holidays, geopy, python-geohash, h3, textblob, vaderSentiment, spacy, pywaffle, pingouin, river, evidently, fastapi, bentoml, onnxruntime, pytorch-tabnet, tensorflow, torch, gensim, openai, cohere, dask, ray, faiss, and includes scripts (resource) and references (resource) and templates (resource) and data (resource) and evals (resource) components.

What problem does it solve?

This Skill streamlines the entire data science and machine learning workflow, from initial data exploration to model deployment strategy, making complex data tasks more accessible and efficient.

Core Features & Use Cases

  • Automated EDA: Generates comprehensive data profiles, identifies quality issues, and suggests cleaning steps.
  • Model Selection & Feature Engineering: Recommends appropriate ML models and guides the creation of effective features.
  • Statistical Analysis & Experiment Design: Assists with hypothesis testing, experiment design, and power analysis.
  • MLOps Guidance: Provides strategies for model deployment, monitoring, and lifecycle management.
  • Use Case: A data analyst needs to understand a new customer dataset, select a model to predict churn, and plan how to deploy it. This Skill can guide them through profiling the data, recommending a suitable model like LightGBM, suggesting feature transformations, and outlining an MLOps strategy.

Quick Start

Use the data-wizard skill to perform an EDA on the file 'customer_data.csv'.

Frequently Asked Questions about data-wizard

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

FAQPage Schema
How do I perform exploratory data analysis and feature engineering on a new dataset?▼

Exploratory data analysis and feature engineering are handled by classifying query complexity and adapting the approach based on data characteristics. It generates data profiles, identifies quality issues, suggests cleaning steps, and guides effective feature transformations for machine learning workflows.

What is the best way to select a machine learning model for predicting customer churn?▼

Model selection for predicting churn involves recommending appropriate algorithms like LightGBM, XGBoost, or CatBoost based on data characteristics. It evaluates query complexity to suggest suitable models, feature transformations, and statistical analysis for your dataset.

Does this MLOps workflow support time series forecasting and anomaly detection?▼

Time series forecasting and anomaly detection are supported through dedicated modes utilizing Prophet, PyTorch forecasting, and HDBSCAN. These integrate into the broader MLOps workflow, providing strategies for model deployment, monitoring, and lifecycle management.

Can I use statistical analysis and experiment design for hypothesis testing in Python?▼

Statistical analysis and experiment design for hypothesis testing are supported using statsmodels, scipy, and pingouin. It assists with hypothesis testing, experiment design, and power analysis by adapting analytical depth to the specific query complexity.

What are the limitations of automated EDA for large-scale data processing?▼

Automated EDA for large-scale data leverages Dask and Ray for distributed computing, but limitations arise from memory constraints and cluster configuration. It classifies query complexity to adapt analysis depth, though extreme scale may require manual optimization beyond standard profiling.

Related Skills

Explore More Data & Analytics Skills→
Mohamed-ElkahefMohamed-Elkahef

csv-data-visualizer

Generate interactive Plotly visualizations and statistical profiles from CSV datasets.

Community
Intermediate
h4vzzh4vzz
33

model-deployment

Deploy trained ML models as REST services on Docker or Kubernetes.

Community
Advanced
icyzhicyzh
1

chroma

Manage vector embeddings for retrieval-augmented generation and semantic search.

Community
Intermediate
Zeyuyang-0420Zeyuyang-0420

timesfm-forecasting

Forecast univariate time series with Google's TimesFM zero-shot model.

Community
Advanced