Garmin Connect Health Data Skill#

Fetch comprehensive health & fitness data from Garmin Connect for your AI agent.

Data Coverage#

CategoryFieldsActivitySteps, distance, calories (active + BMR), floors, intensity minutesHeart RateMin/max/resting heart rateSleepDuration, score, deep/light/REM/awake breakdown, stress during sleepHRVLast night avg, 5min peak, weekly avg, status (balanced/unbalanced), baselineBody BatteryCurrent level, daily min/maxSpO2Average and minimum blood oxygenRespirationWaking and sleep breathing rateStressAverage/max, rest/low/medium/high duration breakdownTraining StatusOverreaching/Highly Active/Productive/Maintaining/Recovery/Detraining + acute/chronic load ratioTraining ReadinessScore (0-100)Fitness MetricsVO2 Max, fitness age, endurance score, hill scoreRace Predictions5K/10K/Half/Marathon predicted timesWeight/Body CompWeight (kg), body fat %, BMI (requires Garmin Index scale)HydrationIntake (ml) vs goalActivitiesIndividual workouts with HR, duration, calories, elevation, training effect, and detail JSONWeekly SummaryTotal/avg steps for the weekSQLite Tablesdaily_summary, activities, and activity_sets for queryable local analysis

Setup#

1. Install dependency#

bash

pip install "garminconnect>=0.3.11"

2. Set credentials (choose one method)#

Option A -- Environment variables:

bash

export GARMIN_EMAIL="you@example.com"
export GARMIN_PASSWORD="yourpassword"

Option B -- CLI args:

bash

python3 garmin_health.py --email you@example.com --password yourpassword

Option C -- macOS Keychain:

bash

security add-generic-password -a "you@example.com" -s "garmin_connect" -w "yourpassword"

Option D -- Credentials file:

bash

echo -e "email=you@example.com\npassword=yourpassword" > ~/.garmin_credentials
chmod 600 ~/.garmin_credentials

3. Set region (China accounts only)#

If your Garmin account was registered in China, add this to your shell profile ( ~/.zshrc / ~/.bashrc) once:

bash

export GARMIN_IS_CN=true

This tells the skill to use connect.garmin.com.cn instead of the global endpoint -- more reliable for mainland China IPs and prevents 429 rate-limit errors. Skip this step if you have a global Garmin account.

4. First run#

First login may require MFA verification. You'll be prompted to enter a code sent to your email.

garminconnect 0.3.x uses native authentication and cannot reuse legacy Garth token files. Upgrading from 0.2.x requires one new interactive login and MFA challenge.

5. Use with OpenClaw#

Ask your AI agent:

• "Show my health data"
• "How did I sleep last night?"
• "What's my HRV?"
• "Am I overtraining?"

Usage#

bash

# Fetch today's data (default)
python3 garmin_health.py

# Fetch specific date
python3 garmin_health.py --date 2026-03-16

# Show latest cached data
python3 garmin_health.py --show

# Use Garmin Connect CN endpoint (Chinese accounts / mainland China IP)
python3 garmin_health.py --cn

# With credentials
python3 garmin_health.py --email you@example.com --password pass

Data Storage#

• ~/.garmin_health/YYYY-MM-DD.json -- Daily JSON snapshots
• ~/.garmin_health/latest.json -- Most recent JSON snapshot
• ~/.garmin_health/garmin.db -- SQLite database with daily_summary, activities, and activity_sets tables
• ~/.garminconnect/ -- OAuth token cache

Override with env vars:

• GARMIN_DATA_DIR -- Change data directory
• GARMIN_TOKENSTORE -- Change token cache directory
• GARMIN_IS_CN=true -- Use Garmin Connect CN endpoint (set once in shell profile)

Supported Languages#

All labels and output in English. JSON field names are English by design.

Security & Privacy#

• Your credentials only -- this skill authenticates with Garmin Connect using your own account credentials. No credentials are shared with or stored by this skill.
• Local storage only -- all fetched health data is saved as JSON/SQLite files on your own machine. No data is sent to any third party.
• Token caching -- after first login, an OAuth token is cached locally ( ~/.garminconnect/). Subsequent runs reuse this token and do not re-send your password.
• Recommended auth -- use macOS Keychain or environment variables rather than --password CLI flag to avoid password exposure in shell history.
• Official API only -- all requests go directly to connect.garmin.com (or connect.garmin.com.cn for CN accounts). No proxies or intermediaries.

Requirements#

• Python 3.10+
• garminconnect >= 0.3.11
• A Garmin Connect account
• Device: Any Garmin watch/fitness tracker synced to Garmin Connect