stacks/data-research
For analysts, researchers, and ML builders working with data
The only stack in any directory with HuggingFace, Kaggle, and D3 bundled together. Interactive D3 visualisations instead of static matplotlib. HuggingFace integration for model training and evaluation. Kaggle dataset discovery built in. Exclusive to theskills.directory.
install entire stack
$ anthropics/skills/xlsx
Analyze CSV files and generate insights with automatic visualizations, statistics, and data profiling.
Create interactive data visualizations, charts, and dashboards using D3.js.
Automate Google Sheets operations via CLI — read, write, format, and manage spreadsheets programmatically.
Complete Kaggle integration — competition reports, dataset downloads, notebook execution, and submissions.
Create structured training datasets with prompts, templates, and validation scripts for ML models.
Comprehensive LLM training skill with guidance, helper scripts, cost estimators, and best practices.
Orchestrate ML model evaluation jobs — benchmarks, metrics, reports, and comparison dashboards.
Collection of scientific skills for working with specialized libraries, databases, and research workflows.
Create, read, edit, and manipulate spreadsheet files (.xlsx, .csv, .tsv) with formulas, charts, and data transformations.
Data scientists don't need another matplotlib chart. They need interactive visualisations, model training pipelines, dataset discovery, and reproducible research workflows. The Data & Research stack is the only stack in any directory with HuggingFace, Kaggle, and D3 bundled together — all exclusive to theskills.directory.
Analysts, researchers, and ML builders working with datasets, models, and data pipelines. Particularly useful for anyone doing research that ends in a paper, a model card, or a shareable visualisation.