3. Data, Science & AI

Extracts EXIF metadata from images including GPS coordinates and timestamps, maps locations, and strips sensitive data for privacy.

Compares multiple machine learning models, performs cross-validation, and selects the optimal model using evaluation metrics for classification or regression tasks.

Automates feature engineering by generating encodings, scaling, polynomial features, and interaction terms for machine learning pipelines.

Analyzes text sentiment (positive/negative/neutral) with emotion detection and visualizations for single or batch processing.

Compares document similarity using TF-IDF, cosine similarity, and Jaccard index for plagiarism and duplicate detection.

Generates customizable word clouds from text with shape, color, font, and stopword filtering options, supporting PNG/SVG export for data visualization.

Standardizes and formats phone numbers globally with validation and multiple output formats for consistent data handling.

Converts unstructured address strings into standardized components (street, city, state, zip, country) with validation for accuracy.

Analyzes and groups data using K-Means, DBSCAN, and hierarchical clustering for customer segmentation and pattern discovery.

Converts physical units (length, mass, temperature, time) for scientific calculations and data transformation.

Calculates geographic distances between coordinates, finds nearby points, and computes travel distances for logistics and location analysis.

Creates publication-ready scientific figures, charts, and visualizations for research papers and academic work.

Dynamically analyzes econometric tasks using RAG, Python, and Stata, then generates Chinese reports.

Extracts tables from PDFs and images (including scanned documents via OCR) and converts to CSV or Excel, supporting complex structures and multi-page documents.

Explains machine learning model predictions through SHAP values, feature importance analysis, and visual decision paths for enhanced model interpretability.

Generates professional PDF/HTML reports with data visualizations, tables, and narrative text using customizable templates and branding for automated reporting.

Queries Bruce Hansen's econometrics textbook RAG database, returning relevant document excerpts upon 'rag:' prefix.

Analyzes survey responses using Likert scale, cross-tabulations, sentiment scoring, and visualizations for actionable insights.

Analyzes expense data from CSV/Excel to categorize spending, identify trends, and provide savings recommendations.

Extracts topics from text collections using LDA, including keyword extraction and topic visualization.

Decomposes time series data into trend, seasonal, and residual components for forecasting and seasonality analysis.

Guides configuration of Claude Code agents with system prompts, tool restrictions, model selection, and MCP integrations for tailored AI interactions.

Handles creation, editing, and analysis of Excel spreadsheets with formulas, formatting, data analysis, and visualization capabilities.

Creates and refines YAML-based definitions for Claude Code sub-agents, ensuring adherence to Anthropic best practices for AI assistant design.