Skip to main content Accueil Créateurs thinkfleetai thinkfleet-engine garmin-health-analysis
garmin-health-analysis Talk to your Garmin data naturally - "what was my fastest speed snowboarding?", "how did I sleep last night?", "what was my heart rate at 3pm?". Access 20+ metrics (sleep stages, Body Battery, HRV, VO2 max, training readiness, body composition, SPO2), download FIT/GPX files for route analysis, query elevation/pace at any point, and generate interactive health dashboards. From casual "show me this week's workouts" to deep "analyze my recovery vs training load".
Aller à l'installation Skills Marketplace Découvrez et explorez les compétences IA créées par la communauté.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Afficher les détails du prompt Une commande directe contourne le prompt de vérification. Examinez la source avant de l'exécuter.
npx skills add https://github.com/ThinkfleetAI/thinkfleet-engine --skill garmin-health-analysisLa commande reste sur une seule ligne. Faites défiler horizontalement pour la vérifier avant de la copier.
Vous préférez une copie locale ? Téléchargez les fichiers actuellement disponibles dans SkillsMP.
Télécharger Zip Téléchargement... Plus depuis ce dépôt Use when working with Resend email platform - routes to specific sub-skills for sending, receiving, audiences, or broadcasts.
Control Bambu Lab 3D printers locally via MQTT (no cloud). Supports A1, A1 Mini, P1P, P1S, X1C.
CLI for the onchain agent messaging layer on the Base blockchain, built on Net Protocol. Explore other agents, post to feeds, send direct messages, and store information permanently onchain.
Métiers associés SOC
Basé sur la classification professionnelle SOC
name garmin-health-analysis description Talk to your Garmin data naturally - "what was my fastest speed snowboarding?", "how did I sleep last night?", "what was my heart rate at 3pm?". Access 20+ metrics (sleep stages, Body Battery, HRV, VO2 max, training readiness, body composition, SPO2), download FIT/GPX files for route analysis, query elevation/pace at any point, and generate interactive health dashboards. From casual "show me this week's workouts" to deep "analyze my recovery vs training load". version 1.2.2 author EversonL & Claude homepage https://github.com/eversonl/ThinkFleet-garmin-health-analysis metadata {"thinkfleet":{"emoji":"⌚","requires":{"env":["GARMIN_EMAIL","GARMIN_PASSWORD"]},"install":[{"id":"garminconnect","kind":"python","package":"garminconnect","label":"Install garminconnect (pip)"},{"id":"fitparse","kind":"python","package":"fitparse","label":"Install fitparse (pip)"},{"id":"gpxpy","kind":"python","package":"gpxpy","label":"Install gpxpy (pip)"}]}}
Garmin Health Analysis
Query health metrics from Garmin Connect and generate interactive HTML charts.
Two Installation Paths This skill supports two different setups :
ThinkFleet Skill (this guide) - Use with ThinkFleet for automation and proactive health monitoringMCP Server (see MCP setup guide ) - Use with standard Claude Desktop as an MCP server Choose the path that matches your use case. You can also use both simultaneously!
ThinkFleet Skill Setup (first time only)
1. Install Dependencies pip3 install garminconnect
2. Configure Credentials You have three options to provide your Garmin Connect credentials:
Option A: ThinkFleet Config (Recommended - UI configurable) Add credentials to ~/.thinkfleet/thinkfleet.json:
{
"skills" : {
"entries" : {
"garmin-health-analysis" : {
"enabled" : true ,
"env" : {
"GARMIN_EMAIL" : "your-email@example.com" ,
"GARMIN_PASSWORD" : "your-password"
}
}
}
}
}
Tip : You can also set these through the ThinkFleet UI in the Skills settings panel.
Option B: Local Config File Create a config file in the skill directory:
cd ~/.thinkfleet/skills/garmin-health-analysis
cp config.example.json config.json
{
"email" : "your-email@example.com" ,
"password" : "your-password"
}
Note : config.json is gitignored to keep your credentials secure.
Option C: Command Line Pass credentials directly when authenticating:
python3 scripts/garmin_auth.py login \
--email YOUR_EMAIL@example.com \
--password YOUR_PASSWORD
3. Authenticate Login to Garmin Connect and save session tokens:
python3 scripts/garmin_auth.py login
This uses credentials from (in priority order):
Command line arguments (--email, --password)
Local config file (config.json)
Environment variables (GARMIN_EMAIL, GARMIN_PASSWORD)
ThinkFleet config (skills.entries.garmin-health-analysis.env)
Session tokens are stored in ~/.thinkfleet/garmin-tokens.json and auto-refresh.
Check authentication status:
python3 scripts/garmin_auth.py status
Fetching Data Use scripts/garmin_data.py to get JSON data:
python3 scripts/garmin_data.py sleep --days 14
python3 scripts/garmin_data.py body_battery --days 30
python3 scripts/garmin_data.py hrv --days 30
python3 scripts/garmin_data.py heart_rate --days 7
python3 scripts/garmin_data.py activities --days 30
python3 scripts/garmin_data.py stress --days 7
python3 scripts/garmin_data.py summary --days 7
python3 scripts/garmin_data.py sleep --start 2026-01-01 --end 2026-01-15
python3 scripts/garmin_data.py profile
Output is JSON to stdout. Parse it to answer user questions.
Generating Charts Use scripts/garmin_chart.py for interactive HTML visualizations:
python3 scripts/garmin_chart.py sleep --days 30
python3 scripts/garmin_chart.py body_battery --days 30
python3 scripts/garmin_chart.py hrv --days 90
python3 scripts/garmin_chart.py activities --days 30
python3 scripts/garmin_chart.py dashboard --days 30
python3 scripts/garmin_chart.py dashboard --days 90 --output ~/Desktop/garmin-health.html
Charts open automatically in the default browser. They use Chart.js with a modern gradient design, stat cards, and interactive tooltips.
Answering Questions User asks Action "How did I sleep last night?" garmin_data.py summary --days 1, report sleep hours + score"How's my recovery this week?" garmin_data.py body_battery --days 7, report average + trend"Show me my health for the last month" garmin_chart.py dashboard --days 30"Is my HRV improving?" garmin_data.py hrv --days 30, analyze trend"What workouts did I do this week?" garmin_data.py activities --days 7, list activities with details"How's my resting heart rate?" garmin_data.py heart_rate --days 7, report average + trend
Key Metrics
Body Battery (0-100) Garmin's proprietary recovery metric based on HRV, stress, sleep, and activity:
High (75-100) : Fully recharged, ready for high intensityMedium (50-74) : Moderate energy, good for regular activityLow (25-49) : Limited energy, recovery neededVery Low (0-24) : Depleted, prioritize rest
Sleep Scores (0-100) Overall sleep quality based on duration, stages, and disturbances:
Excellent (90-100) : Optimal restorative sleepGood (80-89) : Quality sleep with minor issuesFair (60-79) : Adequate but could improvePoor (0-59) : Significant sleep deficiencies
HRV (Heart Rate Variability) Measured in milliseconds, higher is generally better:
Indicates nervous system balance and recovery capacity
Track trends over time (increasing = improving recovery)
Affected by sleep, stress, training load, illness
Normal range varies by individual (20-200+ ms)
Resting Heart Rate (bpm) Lower generally indicates better cardiovascular fitness:
Athletes : 40-60 bpmFit adults : 60-70 bpmAverage adults : 70-80 bpmSudden increases may indicate stress, illness, or overtraining
Stress Levels Based on HRV analysis throughout the day:
Low stress : Rest and recovery periodsMedium stress : Normal daily activitiesHigh stress : Physical activity or mental pressure
Health Analysis When users ask for insights or want to understand their trends, use references/health_analysis.md for:
Science-backed interpretation of all metrics
Normal ranges by age and fitness level
Pattern detection (weekly trends, recovery cycles, training load balance)
Actionable recommendations based on data
Warning signs that suggest rest or medical consultation
Analysis workflow
Fetch data: python3 scripts/garmin_data.py summary --days N
Read references/health_analysis.md for interpretation framework
Apply the analysis framework: Status → Trends → Patterns → Insights → Recommendations
Always include disclaimer that this is informational, not medical advice
Troubleshooting
Authentication Issues
"Invalid credentials" : Double-check email/password, try logging into Garmin Connect web"Tokens expired" : Run login again: python3 scripts/garmin_auth.py login ..."Too many requests" : Garmin rate-limits; wait a few minutes and try again
Missing Data
Some metrics require specific Garmin devices (Body Battery needs HRV-capable devices)
Historical data may have gaps if device wasn't worn
New accounts may have limited history
Library Issues
If garminconnect import fails: pip3 install --upgrade garminconnect
Garmin occasionally changes their API; update the library if requests fail
Privacy Note
Credentials are stored locally in ~/.thinkfleet/garmin-tokens.json
Session tokens refresh automatically
No data is sent anywhere except to Garmin's official servers
You can revoke access anytime by deleting the tokens file
Comparison: Garmin vs Whoop Feature Garmin Whoop Recovery metric Body Battery (0-100) Recovery Score (0-100%) HRV tracking Yes (nightly average) Yes (detailed) Sleep stages Light, Deep, REM, Awake Light, SWS, REM, Awake Activity tracking Built-in GPS, many sport modes Strain score (0-21) Stress All-day stress levels Not directly tracked API Unofficial (garminconnect) Official OAuth Device types Watches, fitness trackers Wearable band only
References
references/api.md — Garmin Connect API details (unofficial)references/health_analysis.md — Science-backed health data interpretationgarminconnect library — Python API wrapperGarmin Connect — Official web interface
Version Info
Created : 2026-01-25Author : EversonL & ClaudeVersion : 1.2.0Dependencies : garminconnect, fitparse, gpxpy (Python libraries)License : MIT 