Data-Science plugins

Find DataMagic recipes, adapt them to your data, and compose editable video stories.

1 skill

Claude Code plugin for Kaggle competition workflows.

1 skill

Run metadata-aware predictions and fine-tune AlphaGenome-PyTorch on custom genomic tracks.

2 skills

Workflow skills for ML experimentation with skrub, scikit-learn, and skore: pipeline build / evaluate / test / audit, iteration loop, workspace + tooling.

26 skills

Workflow skills for ML experimentation with skrub, scikit-learn, and skore: pipeline build / evaluate / test / audit, iteration loop, workspace + tooling.

28 skills

Discover causal structure in nonstationary time series with causal-ts — data-health inspection, algorithm/CI-test selection, discovery, and graph interpretation.

1 skill

Independent, unofficial Kaggle.com plugin: research a competition, see where you stand, check and submit with a dry run first, read solution writeups and discussions, and work with datasets, models and notebooks. Not affiliated with, endorsed by, or sponsored by Kaggle or Google.

1 skill · 1 MCP server

Run Stata from Claude Code through the stata-code MCP server (23 tools, 14 workflow prompts, typed errors, token-economy logs/graphs, multi-session) and an agent skill that teaches Claude the result schema and modern DiD/IV/RDD/table workflows, including StatsPAI cross-validation.

1 skill · 1 MCP server

Turn your agent into a senior geospatial data scientist: 18 skills for the full GeoAI lifecycle, including guarded ArcGIS Pro automation, with spatial failure modes designed out.

18 skills

Expert agents and comprehensive skills for interactive data visualization using the HoloViz ecosystem including Panel, hvPlot, HoloViews, Datashader, GeoViews, Colorcet, and Lumen.

9 skills · 9 commands · 4 agents · 1 MCP server

Benchmarking and optimization tools for Zarr chunking strategies on cloud object stores. Measures performance across access patterns and generates recommendations based on Nguyen et al. (2023) methodology.

5 skills · 5 commands · 2 agents

Comprehensive agents and skills for working with the Zarr array storage format — creation, compression, cloud backends, xarray integration, and data migration

5 skills · 2 agents

Data science and data engineering agents for visualization (D3, Highcharts), notebooks (Jupyter, Google Colab), R, and Python data engineering.

6 agents

데이터 프로파일링 및 탐색적 데이터 분석(EDA)을 수행합니다. ydata-profiling 기반 자동 리포트 생성 및 인터랙티브 분석을 제공합니다.

1 skill · 2 commands · 2 agents

Singapore HDB, private-property, neighbourhood, and mortgage tools and skills.

2 skills · 1 MCP server

Feature Engineering 및 데이터 전처리 파이프라인을 구축합니다. 스케일링, 인코딩, Feature 생성 등을 자동화합니다.

1 command · 1 agent

Singapore company, UEN, sector, retail, tourism, and business-context tools and skills.

1 skill · 1 MCP server

Singapore economy, prices, employment, income, trade, and population tools and skills.

1 skill · 1 MCP server

클래스 불균형 문제를 해결합니다. SMOTE, ADASYN 등 다양한 리샘플링 기법을 제공합니다.

1 command

Task-oriented skills (simulation, estimation, reporting, interop with NONMEM/Monolix, optimal design) and an orchestrating agent for the nlmixr2 ecosystem.

5 skills

Task-oriented skills (simulation, estimation, reporting, interop with NONMEM/Monolix) and an orchestrating agent for the nlmixr2 ecosystem.

4 skills

Rigorous methods for statistics, machine learning, and meta-analysis, from question to paper: pre-specified SAPs, statistical and reporting-checklist review, and reproducible R and Python workflows. Every study compounds.

70 skills · 55 agents · hooks

Expert agents for R data science and biostatistics covering data wrangling, feature engineering, model building, statistical evaluation, clinical trials, genomics, documentation generation, and reproducible reporting using tidyverse and tidymodels. All agents create new code in output folders - never modifying existing user code.

23 skills · 7 commands · 10 agents

Multi-domain skill and agent library. Kaggle: 12 competition skills + 3 agents (EDA, baselines, Optuna, feature engineering, ensembling, pseudo-labeling). SDLC: 17 agents + 4 skills across 4 phases (requirements → architecture → implementation → review). Research: paper writing with live web search for guidelines, literature review, and venue selection across IEEE, ACM, Nature, Springer, Elsevier, NeurIPS, ICML, and more.

18 skills

Stata skills: turns a plain-language data/statistics task into correct, runnable Stata code, with good-vs-bad command guidance, Python↔Stata interop, and a growing recipe library (ARDL, time-series and panel regression, unit-root tests).

Compound engineering for computational scientists: reproducible, compliant, compound research automation with R/Python statistical review and SAP tracking.

65 skills · 55 agents · hooks

Full ML lifecycle workbench — research papers, datasets, data prep, train (full supervised learning coverage), evaluate, explain, deploy, drift detection, LLM fine-tuning, MCP server builder, context engineering, and interactive ML courses. 11 agents, 16 skills, 3 CLI tools, Python LSP.

18 skills · 11 agents · 2 MCP servers · hooks · LSP

Expert-level guidance for building interactive data visualizations and dashboards with the HoloViz ecosystem. Covers Panel, HoloViews, hvPlot, GeoViews, Datashader, Lumen, Param, and Colorcet with integrated MCP server support for real-time library introspection.

9 skills · 4 agents · 3 MCP servers

A Claude Code plugin for end-to-end data analysis workflows.

12 skills

Makes the agent a rigorous data scientist (frame, look, leakage-check, baseline, honest validation) and drives live Jupyter/JupyterLab/editor notebooks.

10 skills · 1 MCP server · hooks