Agent skill · data analytics · jeremylongshore
running-clustering-algorithms
Analyze datasets by running clustering algorithms (K-means, DBSCAN,
Why this skill is useful
Adds specific implementations for K-means, DBSCAN, and hierarchical clustering that the AI wouldn't reliably generate on its own.
What it needs
Requires python, scikit-learn installed locally. About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Clustering Algorithm Runner Run clustering algorithms (K-means, DBSCAN, hierarchical) on datasets to discover natural groupings and structure in data. Overview This skill empowers Claude to perform clustering analysis on provided datasets. It allows for automated execution of various clustering algorithms, providing insights into data groupings and structures. How It Works 1. Analyzing the Context: Claude analyzes the user's request to determine the dataset, desired clustering algorithm (if specified), and any specific requirements. 2. Generating Code: Claude generates Python code using appropriate ML libraries (e.g., scikit-learn) to perform the clustering task, including data loading, preprocessing, algorithm execution, and result visualization. 3. Executing Clustering: The generated code is executed, and the clustering algorithm is applied to the dataset. 4. Providing Results: Claude presents the results, including cluster assignments, performance metrics (e.g., silhouette score, Davies-Bouldin index), and visualizations (e.g., scatter plots with cluster labels). When to Use This Skill This skill activates when you need to: Identify distinct groups within a dataset. Perform a cluster analysis to understand data structure. Run K-means, DBSCAN, or hierarchical clustering on a given dataset. Examples Example 1: Customer Segmentation User request: "Run clustering on this customer data to identify customer segments. The data is in customerdata.csv." The skill will: 1. Load the customerdata.csv dataset. 2. Perform K-means clustering to identify distinct customer segments based on their attributes. 3. Provide a visualization of the customer segments and their characteristics. Example 2: Anomaly Detection User request: "Perform DBSCAN clustering on this network traffic data to identify anomalies. The data is available at networktraffic.txt." The skill will: 1. Load the networktraffic.txt dataset. 2. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/running-clustering-algorithms--767029