Garmer

Extract health and fitness data from Garmin Connect including activities, sleep, heart rate, stress, steps, and body composition. Use when the user asks about their Garmin data, fitness metrics, sleep analysis, or health insights.

Security Scan

The skill appears to implement a legitimate Garmin Connect data extractor, but there are inconsistencies between the SKILL.md and the registry metadata (and some packaging/installation details) that warrant caution before installing or granting credentials.

Purpose & Capability

The name/description, code, and README consistently describe a Garmin Connect data extractor that needs a Garmin account and tokens; that capability aligns with the requested behavior. However, the registry metadata (shown at the top of the submission) lists no required env vars or primary credential while the SKILL.md declares a primaryEnv (GARMER_TOKEN_DIR) and the code/README reference token files (~/.garmer/garmin_tokens) and interactive login. This mismatch (registry claims no credentials required but the skill clearly needs Garmin credentials/tokens) is an inconsistency to be aware of.

Instruction Scope

SKILL.md and examples instruct the agent to run the 'garmer' CLI and Python API to authenticate (interactive email/password via 'garmer login'), read saved tokens from ~/.garmer/garmin_tokens (or a directory set by GARMER_TOKEN_DIR), and fetch health data. The instructions are scoped to the stated purpose (fetching Garmin data) and do not instruct the agent to read unrelated system files or send data to unexpected endpoints. They do, however, require collecting user credentials (email/password) for Garmin and storing tokens locally.

Install Mechanism

No separate install spec was present in the registry metadata summary, but SKILL.md includes install metadata for pip/uv and the package contains a standard Python project (pyproject.toml) and a console script entry point. Installing via pip (from PyPI or local source) is a standard pattern and not inherently high risk; there is no evidence of arbitrary URL downloads or extraction from untrusted servers. The inconsistency between 'no install spec' in the registry summary and install metadata inside SKILL.md is a packaging/metadata mismatch that should be confirmed.

Credentials

The skill needs only Garmin credentials/tokens and optionally a token directory env var (GARMER_TOKEN_DIR) and logging/cache env vars referenced in README. It does not request unrelated cloud credentials or other secrets. That is proportionate to its purpose. Again, the registry-level declaration of 'no required env vars' contradicts the SKILL.md/readme which list GARMER_TOKEN_DIR and describe token storage; confirm which declaration is authoritative.

Persistence & Privilege

The skill does not request always: true and does not attempt to modify other skills or global agent config. It stores OAuth tokens under ~/.garmer/garmin_tokens (or a custom directory) for reuse; this is expected for a client that needs persistent auth. Note that autonomous invocation is enabled by default (disable-model-invocation: false) — this is platform normal behavior, but you should be comfortable with an installed skill being invoked by the agent when appropriate.

What to consider before installing

This package appears to be a real Garmin Connect data extractor, but the registry metadata and the SKILL.md/README disagree about what is required. Before installing or using it: 1) Confirm the package source and author (the registry shows an anonymous owner id and no homepage). 2) Inspect the code (you have the source here) or run it in an isolated environment if you will provide your Garmin credentials. 3) Understand that you will need to enter your Garmin email/password during 'garmer login' and that tokens will be stored under ~/.garmer/garmin_tokens or a directory set via GARMER_TOKEN_DIR — treat those tokens as sensitive and revoke them in your Garmin account if needed. 4) Prefer installing from a trusted package index or from source you control, and consider running the tool inside a VM or container if you are unsure about provenance. If you want, I can highlight any code files or functions to review first (authentication flow, network endpoints used, and token storage/refresh logic).

Garmer - Garmin Data Extraction Skill

This skill enables extraction of health and fitness data from Garmin Connect for analysis and insights.

Prerequisites

1. A Garmin Connect account with health data
2. The garmer CLI tool installed (see installation options in metadata)

Authentication (One-Time Setup)

Before using garmer, authenticate with Garmin Connect:

garmer login

This will prompt for your Garmin Connect email and password. Tokens are saved to ~/.garmer/garmin_tokens for future use.

To check authentication status:

garmer status

Available Commands

Daily Summary

Get today's health summary (steps, calories, heart rate, stress):

garmer summary
# For a specific date:
garmer summary --date 2025-01-15
# Include last night's sleep data:
garmer summary --with-sleep
garmer summary -s
# JSON output for programmatic use:
garmer summary --json
# Combine flags:
garmer summary --date 2025-01-15 --with-sleep --json

Sleep Data

Get sleep analysis (duration, phases, score, HRV):

garmer sleep
# For a specific date:
garmer sleep --date 2025-01-15

Activities

List recent fitness activities:

garmer activities
# Limit number of results:
garmer activities --limit 5
# Filter by specific date:
garmer activities --date 2025-01-15
# JSON output for programmatic use:
garmer activities --json

Activity Detail

Get detailed information for a single activity:

# Latest activity:
garmer activity
# Specific activity by ID:
garmer activity 12345678
# Include lap data:
garmer activity --laps
# Include heart rate zone data:
garmer activity --zones
# JSON output:
garmer activity --json
# Combine flags:
garmer activity 12345678 --laps --zones --json

Health Snapshot

Get comprehensive health data for a day:

garmer snapshot
# For a specific date:
garmer snapshot --date 2025-01-15
# As JSON for programmatic use:
garmer snapshot --json

Export Data

Export multiple days of data to JSON:

# Last 7 days (default)
garmer export

# Custom date range
garmer export --start-date 2025-01-01 --end-date 2025-01-31 --output my_data.json

# Last N days
garmer export --days 14

Utility Commands

# Update garmer to latest version (git pull):
garmer update

# Show version information:
garmer version

Python API Usage

For more complex data processing, use the Python API:

from garmer import GarminClient
from datetime import date, timedelta

# Use saved tokens
client = GarminClient.from_saved_tokens()

# Or login with credentials
client = GarminClient.from_credentials(email="[e-mail]", password="pass")

User Profile

# Get user profile
profile = client.get_user_profile()
print(f"User: {profile.display_name}")

# Get registered devices
devices = client.get_user_devices()

Daily Summary

# Get daily summary (defaults to today)
summary = client.get_daily_summary()
print(f"Steps: {summary.total_steps}")

# Get for specific date
summary = client.get_daily_summary(date(2025, 1, 15))

# Get weekly summary
weekly = client.get_weekly_summary()

Sleep Data

# Get sleep data (defaults to today)
sleep = client.get_sleep()
print(f"Sleep: {sleep.total_sleep_hours:.1f} hours")

# Get last night's sleep
sleep = client.get_last_night_sleep()

# Get sleep for date range
sleep_data = client.get_sleep_range(
    start_date=date(2025, 1, 1),
    end_date=date(2025, 1, 7)
)

Activities

# Get recent activities
activities = client.get_recent_activities(limit=5)
for activity in activities:
    print(f"{activity.activity_name}: {activity.distance_km:.1f} km")

# Get activities with filters
activities = client.get_activities(
    start_date=date(2025, 1, 1),
    end_date=date(2025, 1, 31),
    activity_type="running",
    limit=20
)

# Get single activity by ID
activity = client.get_activity(12345678)

Heart Rate

# Get heart rate data for a day
hr = client.get_heart_rate()
print(f"Resting HR: {hr.resting_heart_rate} bpm")

# Get just resting heart rate
resting_hr = client.get_resting_heart_rate(date(2025, 1, 15))

Stress & Body Battery

# Get stress data
stress = client.get_stress()
print(f"Avg stress: {stress.avg_stress_level}")

# Get body battery data
battery = client.get_body_battery()

Steps

# Get detailed step data
steps = client.get_steps()
print(f"Total: {steps.total_steps}, Goal: {steps.step_goal}")

# Get just total steps
total = client.get_total_steps(date(2025, 1, 15))

Body Composition

# Get latest weight
weight = client.get_latest_weight()
print(f"Weight: {weight.weight_kg} kg")

# Get weight for specific date
weight = client.get_weight(date(2025, 1, 15))

# Get full body composition
body = client.get_body_composition()

Hydration & Respiration

# Get hydration data
hydration = client.get_hydration()
print(f"Intake: {hydration.total_intake_ml} ml")

# Get respiration data
resp = client.get_respiration()
print(f"Avg breathing: {resp.avg_waking_respiration} breaths/min")

Comprehensive Reports

# Get health snapshot (all metrics for a day)
snapshot = client.get_health_snapshot()
# Returns: daily_summary, sleep, heart_rate, stress, steps, hydration, respiration

# Get weekly health report with trends
report = client.get_weekly_health_report()
# Returns: activities summary, sleep stats, steps stats, HR trends, stress trends

# Export data for date range
data = client.export_data(
    start_date=date(2025, 1, 1),
    end_date=date(2025, 1, 31),
    include_activities=True,
    include_sleep=True,
    include_daily=True
)

Common Workflows

Health Check Query

When a user asks "How did I sleep?" or "What's my health summary?":

garmer snapshot --json

Activity Analysis

When a user asks about workouts or exercise:

garmer activities --limit 10

Trend Analysis

When analyzing health trends over time:

garmer export --days 30 --output health_data.json

Then process the JSON file with Python for analysis.

Data Types Available

• Activities: Running, cycling, swimming, strength training, etc.
• Sleep: Duration, phases (deep, light, REM), score, HRV
• Heart Rate: Resting HR, samples, zones
• Stress: Stress levels, body battery
• Steps: Total steps, distance, floors
• Body Composition: Weight, body fat, muscle mass
• Hydration: Water intake tracking
• Respiration: Breathing rate data

Error Handling

If not authenticated:

Not logged in. Use 'garmer login' first.

If session expired, re-authenticate:

garmer login

Environment Variables

• GARMER_TOKEN_DIR: Custom directory for token storage
• GARMER_LOG_LEVEL: Set logging level (DEBUG, INFO, WARNING, ERROR)
• GARMER_CACHE_ENABLED: Enable/disable data caching (true/false)

References

For detailed API documentation and MoltBot integration examples, see references/REFERENCE.md.