health

Ingest wearable health data into a local SQLite knowledge graph.

3|2|Updated Mar 17, 2026

Search Tags:#health #longevity #local-first #garmin #training-load #hrv

Ready to run

npx skills add https://github.com/broomva/skills --skill health-broomva

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: health
Source: https://github.com/broomva/skills/tree/main/skills/healthcare/health
Command: npx skills add https://github.com/broomva/skills --skill health-broomva

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pydantic, pydantic-settings, typer, rich, platformdirs, tomli, garth, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the fragmentation of personal health data by providing a local-first, queryable knowledge graph that synthesizes raw wearable data into validated longevity metrics without relying on vendor-controlled coaching surfaces.

Core Features & Use Cases

Trace Ingestion: Automatically pulls and maps raw data from Garmin devices into a secure, local SQLite database.
Longevity Synthesis: Computes validated metrics like HRV-CV, CTL/ATL/TSB training load, and VO2max arcs to track long-term health trends.
Obsidian Projection: Generates daily health summaries directly into your personal knowledge base for human interpretation.

Quick Start

Run the health sync command to pull your latest wearable data and update your local health knowledge graph.

Frequently Asked Questions about health

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I build a local-first health knowledge graph from Garmin wearable data?▼

To build a local-first health knowledge graph, ingest and synthesize personal wearable data from Garmin devices into a secure, local SQLite database using modular hexagonal architecture for diverse health data integration.

How do I calculate training load and HRV metrics for longevity tracking locally?▼

Calculate longevity metrics like HRV-CV, CTL/ATL/TSB training load, and VO2max arcs by synthesizing raw time-series health data within a local SQLite database, avoiding vendor-controlled coaching surfaces.

Can I project daily health summaries from my wearable data into Obsidian?▼

Yes, you can generate daily health summaries directly into your personal Obsidian knowledge base for human interpretation, projecting validated longevity metrics from your local SQLite health graph.

Does this local-first personal health approach require vendor cloud subscriptions?▼

No, it eliminates reliance on vendor-controlled coaching surfaces by automatically pulling and mapping raw Garmin data into a secure, local SQLite database, giving you full queryable ownership of your health metrics.

What is the best way to query VO2max and HRV time-series data without vendor lock-in?▼

The best way to avoid vendor lock-in is ingesting raw wearable traces into a local-first SQLite knowledge graph, enabling independent time-series analysis of VO2max arcs and HRV trends.

Are there limitations when pulling raw health data from Garmin into a local database?▼

Data ingestion is currently specialized for Garmin devices via the garth dependency, meaning users with wearables from other ecosystems cannot utilize the trace ingestion pipeline without modular adaptation.