moai-domain-data-science
Production-grade data science specialist with TensorFlow 2.20.0, PyTorch\ \ 2.9.0, \nScikit-learn 1.7.2 expertise. Master data processing, ML pipeline development,\ \ \nmodel deployment, and statistical analysis. Build end-to-end data science \n\ solutions with comprehensive experimentation and visualization.\n"
npx skills add majiayu000/claude-skill-registry --skill moai-domain-data-science-jg-chalk-io-nora-livekit --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Explains a data science capability focused on end-to-end data science work, including data processing, ML pipeline development, model deployment, and statistical analysis, with emphasis on experimentation and visualization.
How it works
Describes concrete components and workflows the agent should implement:
- Data processing and analysis capabilities using common libraries (Pandas, NumPy, SciPy, etc.).
- Machine learning framework support (TensorFlow, PyTorch, Scikit-learn) for building and evaluating models.
- Visualization tools (Matplotlib, Seaborn, Plotly) for exploratory analysis and results visualization.
- Experimentation tooling (MLflow, Weights & Biases, Neptune) for tracking experiments and results.
- Practical code examples provided for data loading, preprocessing, model training, and evaluation, illustrating end-to-end pipelines.
- Advanced preprocessing, feature engineering, and feature importance assessment are covered in code samples.
- Statistical analysis and hypothesis testing routines are included (descriptive statistics, normality tests, confidence intervals).
When to use it
Use when you need a data science workflow that combines data preprocessing, feature engineering, model training, evaluation, and statistical analysis, with an emphasis on end-to-end experimentation and visualization. Triggered when building end-to-end data science solutions or setting up reproducible ML experiments.
What it can touch
- Tools declared: Read, Write, Edit, Bash, Glob, WebFetch, WebSearch. The skill enumerates Python libraries and example code but does not specify executable commands beyond embedded code blocks. No explicit external API calls or file-system actions are described beyond standard Python data science tasks in the examples.
Caveats
- License: MIT. The material is described as production-grade and references multiple frameworks; no explicit deployment targets or environment setup details beyond typical pipelines are given in the excerpts. No stated performance guarantees or compatibility constraints beyond the listed versions.
# Data Science & Analytics ## Level 1: Quick Reference ### Core Capabilities - **Data Processing**: Pandas 2.2.0, NumPy 1.26.0, Dask 2024.1.0 - **Machine Learning**: TensorFlow 2.20.0, PyTorch 2.9.0, Scikit-learn 1.7.2 - **Visualization**: Matplotlib 3.8.0, Seaborn 0.13.0, Plotly 5.17.0 - **Statistics**: SciPy 1.12.0, Statsmodels 0.14.0, Pingouin 0.8.0 - **Big Data**: Spark 3.5.0, Polars 0.20.0, Apache Arrow 14.0.0 - **Experimentation**: MLflow 2.9.0, Weights & Biases, Neptune ### Quick Setup Examples ```python # Data science workflow starter import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns from sklearn.model_selection import train_test_split from sklearn.ensemble import RandomForestClassifier from sklearn.metrics import classification_report, confusion_matrix # Load and explore data df = pd.read_csv('data.csv') print(f"Dataset shape: {df.shape}") print(f"Missing values: {df.isnull().sum().sum()}") # Basic preprocessing X = df.drop('target', axis=1) y = df['target'] # Split data X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # Train model model = RandomForestClassifier(n_estimators=100, random_st
- Level 1: Quick Reference
- Core Capabilities
- Quick Setup Examples
- Level 2: Practical Implementation
- Data Processing & Analysis Pipeline
- Level 3: Advanced Integration
- Production ML Systems
- Related Skills
- Quick Start Checklist
- Data Science Best Practices
What does the moai-domain-data-science skill do?
Production-grade data science specialist with TensorFlow 2.20.0, PyTorch\ \ 2.9.0, \nScikit-learn 1.7.2 expertise. Master data processing, ML pipeline development,\ \ \nmodel deployment, and statistical analysis. Build end-to-end data science \n\ solutions with comprehensive experimentation and visualization.\n"
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill moai-domain-data-science-jg-chalk-io-nora-livekit --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.