Analyze CSV, JSON, Parquet, or text datasets and generate plain-language reports.
npx skills add https://github.com/milasaurus/compound-ml --skill ml-analyze
Please help me install this Agent Skill. Skill: ml-analyze Source: https://github.com/milasaurus/compound-ml/tree/main/plugins/compound-ml/skills/ml-analyze Command: npx skills add https://github.com/milasaurus/compound-ml --skill ml-analyze
This Skill provides a thorough end-to-end analysis of datasets, uncovering patterns, anomalies, and generating plain-language reports to help users make informed decisions.
Run an analysis on the dataset 'sales_data.csv' to understand customer buying patterns.
High-intent search queries and answers about installing and using this skill.
End-to-end data analysis automatically profiles your CSV, detects patterns and anomalies using clustering, then generates a plain-language report with actionable insights. You simply provide the dataset and describe your analysis objective in natural language.
Yes, data analysis objectives can be specified in natural language. You can describe your goals in plain text, such as asking to find customer buying patterns, and the analysis methods are automatically selected and executed based on that objective.
Pattern detection and anomaly detection support CSV, JSON, Parquet, and text file datasets. The analysis methods are automatically selected based on the specific data type provided in these supported formats.
Yes, Python libraries are required for data manipulation, clustering, and anomaly detection. The analysis relies on dependencies including pandas, sklearn, umap, hdbscan, sentence-transformers, and matplotlib to process data and generate visualizations.
The best way to detect anomalies and uncover patterns in a Parquet dataset is using automated clustering and anomaly detection algorithms. This approach profiles the data, applies hdbscan and umap for pattern recognition, and outputs a detailed report.
milasaurusDetect and explain anomalies in datasets using Isolation Forest and Local Outlier Factor.
doubleG7Integrate AI/ML capabilities into Nirvana modules for predictive analytics and automation.
milasaurusProfile datasets for structure, distributions, and quality with narrative summaries.
TianGzlabPerform univariate statistical tests and FDR correction on metabolomics data.
