garmin-health-analysis

# Garmin Health Analysis

Query health metrics from Garmin Connect and generate interactive HTML charts.

## Two Installation Paths

This skill supports **two different setups**:

1. **Clawdbot Skill** (this guide) - Use with Clawdbot for automation and proactive health monitoring
2. **MCP Server** ([see MCP setup guide](references/mcp_setup.md)) - Use with standard Claude Desktop as an MCP server

Choose the path that matches your use case. You can also use both simultaneously!

---

## Clawdbot Skill Setup (first time only)

### 1. Install Dependencies

```bash
pip3 install garminconnect
```

### 2. Configure Credentials

You have three options to provide your Garmin Connect credentials:

#### Option A: Clawdbot Config (Recommended - UI configurable)

Add credentials to `~/.clawdbot/clawdbot.json`:

```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 Clawdbot UI in the Skills settings panel.

#### Option B: Local Config File

Create a config file in the skill directory:

```bash
cd ~/.clawdbot/skills/garmin-health-analysis
# or: cd <workspace>/skills/garmin-health-analysis
cp config.example.json config.json
# Edit config.json and add your email and password
```

**config.json:**
```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:
```bash
python3 scripts/garmin_auth.py login \
  --email YOUR_EMAIL@example.com \
  --password YOUR_PASSWORD
```

### 3. Authenticate

Login to Garmin Connect and save session tokens:

```bash
python3 scripts/garmin_auth.py login
```

This uses credentials from (in priority order):
1. Command line arguments (`--email`, `--pas...

# Garmin Health Analysis - Clawdbot Skill

> **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 from your Garmin device: sleep stages, Body Battery, HRV, VO2 max, training readiness, body composition, SPO2, and more. Download FIT/GPX files, query elevation/pace at any point, and generate interactive health dashboards.

## 🔵 Looking for Claude Desktop? 

**This is the Clawdbot skill repo.** For standard Claude Desktop, use the dedicated MCP server:

👉 **[garmin-health-mcp-server](https://github.com/eversonl/garmin-health-mcp-server)** - Node.js MCP server for Claude Desktop

---

## 🚀 Clawdbot Installation

**Best for**: Automated health monitoring, scheduled reports, proactive check-ins

```bash
# Install via clawdhub
clawdhub install garmin-health-analysis

# Or manually
cd ~/.clawdbot/skills
git clone https://github.com/eversonl/ClawdBot-garmin-health-analysis.git garmin-health-analysis

# Install dependencies
pip3 install garminconnect fitparse gpxpy

# Configure credentials and authenticate
python3 scripts/garmin_auth.py login
```

**[📖 Full Setup Guide](SKILL.md)**

## ⚡ Features

- **Natural language queries**: "How's my recovery this week?" → instant Body Battery analysis
- **Sleep analysis**: Hours, stages (light/deep/REM), quality scores, trends
- **Recovery tracking**: Body Battery, HRV, training readiness, stress levels
- **Workout data**: Activities by type, calories, duration, pace, elevation
- **Health metrics**: Resting heart rate, VO2 max, body composition, SPO2
- **Activity files**: Download FIT/GPX for detailed route and performance analysis
- **Interactive charts**: Beautiful HTML dashboards with Chart.js visualizations
- **Science-backed insights**: Interpret trends with expert analysis framework

## 📊 Example Queries

**Clawdbot or Claude Desktop:**

> "How did I sleep last night?"
> 
> "Show me my health dashboard for the l...