Profile datasets for structure, distributions, and quality with narrative summaries.
npx skills add https://github.com/milasaurus/compound-ml --skill ml-explore
Please help me install this Agent Skill. Skill: ml-explore Source: https://github.com/milasaurus/compound-ml/tree/main/plugins/compound-ml/skills/ml-explore Command: npx skills add https://github.com/milasaurus/compound-ml --skill ml-explore
This Skill provides automated exploratory data analysis to help you understand and profile your datasets, without requiring ML expertise.
Use the ml-explore skill to profile the data in 'data.csv'.
High-intent search queries and answers about installing and using this skill.
Automated exploratory data analysis profiles your CSV file to identify structure, distributions, and quality issues. This Skill generates plain-language narrative summaries without requiring manual plotting or ML expertise, handling JSON and Parquet formats as well.
Profiling a dataset for plain language insights is done by scanning data structure and distributions to produce narrative summaries. This Skill outputs human-readable reports explaining data quality and characteristics, avoiding complex statistical jargon.
You do not need matplotlib and sentence-transformers to generate a dataset summary; both are optional. Matplotlib provides optional data visualizations, while sentence-transformers enable optional text embeddings, keeping core profiling dependencies minimal.
Using pandas for exploratory data analysis without custom scripts is possible through automated profiling. This Skill leverages pandas internally to inspect datasets and output narrative summaries, eliminating the need to manually code data exploration logic.
Supported data formats for automated data profiling include CSV, JSON, and Parquet files. The Skill reads these file types to analyze data structure, evaluate quality, and deliver narrative summaries detailing dataset distributions.
Automated data profiling is the process of inspecting datasets to understand structure, distributions, and quality. It handles data quality by evaluating the dataset and generating plain-language narrative summaries that highlight findings without requiring complex tools.
Sir-chawakornClean, transform, and reshape CSV, Parquet, and DataFrame tabular data.
Mohamed-ElkahefGenerate interactive Plotly visualizations and statistical profiles from CSV datasets.
handsomelong922Generate embeddings for semantic similarity, clustering, and retrieval with PyTorch.
wachawoProfile dataset structure, completeness, and statistical validity with pandas and numpy.
