Data Analysis

A comprehensive nutrition analyzer that processes local dietary records to identify nutritional trends, evaluate nutrient intake against RDA standards, and generate personalized improvement recommendations. It supports correlation analysis with exercise, sleep, and chronic disease data while maintaining clear medical safety boundaries.

This skill analyzes mental health data from local JSON files to track PHQ-9/GAD-7 assessment scores, identify emotional patterns, evaluate crisis risk levels, and correlate mental health with sleep, exercise, and nutrition. It generates comprehensive reports with actionable recommendations while maintaining clear medical safety boundaries.

A comprehensive health trend analysis skill that tracks weight/BMI, symptoms, medications, lab results, and mood/sleep patterns over time. It reads locally stored health data files and generates interactive HTML reports with ECharts visualizations, correlation analysis, and personalized health recommendations.

This skill enables querying a nutritional food database containing 50 common foods with detailed nutritional data. It supports food lookups by name (Chinese/English), nutritional comparisons between foods, smart recommendations based on health conditions (diabetes, hypertension, etc.), and automatic nutrition calculations for meals with portion size conversion.

This skill analyzes your fitness and exercise data to identify workout trends, track progress over time, and correlate exercise with health metrics like blood pressure and blood sugar. It provides personalized training recommendations based on WHO/ACSM guidelines while respecting medical safety boundaries.

Analyzes family health history data to identify genetic risk patterns, disease clustering, and provides personalized prevention recommendations. Generates visual reports including family trees and risk heatmaps while maintaining clear medical safety boundaries.

An AI-powered health analysis system that integrates multiple health data sources (fitness, sleep, nutrition, mental health) to identify patterns, predict health risks, and provide personalized recommendations. All data processing happens locally with no external API calls.

Analyzes CSV files, generates summary stats, and plots quick visualizations using Python and pandas.