A specialized skill for synchronizing Garmin Connect activity history and training schedules into a structured JSON database.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install garmin-tracker
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install garmin-tracker using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Garmin Tracker?
The Garmin Tracker skill provides a robust bridge between Garmin Connect and your local workspace. It is designed to automate the extraction of running activities and training plans, transforming web-based data into a clean, canonical JSON schema. By utilizing this skill within the ecosystem of Openclaw Skills, users can maintain a precise history of their fitness journey starting from a fixed control date without the overhead of manual data entry.
This skill prioritizes data integrity and security, leveraging Playwright for browser-based scraping while supporting multiple authentication methods. It focuses on essential performance metrics such as distance, duration, heart rate, and pace, ensuring that the resulting dataset is optimized for further analysis or integration into personalized fitness dashboards.
Garmin Tracker Use Cases
- Automatically updating a local garmin_tracking.json file with recent running activities.
- Synchronizing upcoming training plan workouts to stay on top of scheduled fitness goals.
- Validating and reconciling existing fitness data to ensure it adheres to a strict technical schema.
- Generating high-level activity summaries for use in automated status reports or personal performance reviews.
How Garmin Tracker Works
- The skill launches a controlled browser session using Playwright to access the Garmin Connect web portal.
- It scrapes the activity list to identify and extract new sessions recorded since the control date of February 1, 2026.
- The agent navigates to the training plan dashboard to capture the current week's schedule and upcoming assignments.
- A bundled Python reconciliation script processes the raw data, recomputes cumulative totals, and updates the local JSON file.
- The tool performs a final schema validation to ensure all fields like avgPaceSecPerKm and calories are correctly formatted.
Garmin Tracker Setup
To get started with this skill, ensure that Node.js and Python 3 are installed in your environment. You must also install the Playwright core dependency within your workspace:
npm install playwright-core
Once dependencies are ready, you can manually trigger a reconciliation of your tracking file using the provided Python script:
python3 scripts/reconcile_tracking.py --file garmin_tracking.json --write
To sync the training plan from your Garmin account, use the Node.js sync script:
node scripts/sync_training_plan.mjs --file garmin_tracking.json --write
Garmin Tracker Data Schema & Taxonomy
The skill organizes data within a file named garmin_tracking.json at the workspace root. The structure is strictly defined to maintain compatibility across different Openclaw Skills and analysis tools:
| Key | Type | Description |
|---|---|---|
| lastUpdate | String | ISO 8601 timestamp of the last successful sync. |
| planName | String | The name of the active Garmin training program. |
| summary | Object | Aggregated stats (to/from dates, total distance). |
| history | Array | List of completed activities with canonical fields. |
| upcoming | Array | List of scheduled future workouts. |
| recurring_activities | Array | Definitions for standard repeating workout types. |
Each activity in the history array contains specific metrics: type, distanceKm, durationSec, avgPaceSecPerKm, avgHrBpm, calories, and sourceId.
Garmin Tracker Advanced Features
- Sophisticated authentication flow supporting existing browser sessions, manual login, and secure credential fallback.
- Integrated CDP (Chrome DevTools Protocol) resolution for working with remote or containerized browser instances.
- Built-in reconciliation engine for automatic calculation of pace and duration aggregates.
- Local validator scripts to prevent data corruption and ensure strict schema adherence.
- Support for custom configuration profiles to manage multiple browser environments and CDP endpoints.
SKILL.md
Loading
Related Openclaw Skills
bun-do-api
A local-first REST API for managing tasks, recurring payments, and project progress logs with full JSON persistence.
Microsoft Learn MCP
A bridge for AI agents to query, search, and retrieve live Microsoft technical documentation and official code samples.
Excalidraw Diagram Generator
An automated diagramming tool that converts text descriptions into hand-drawn Excalidraw visuals for Obsidian and web platforms.
Terminal Screenshots & Recordings with VHS
A specialized tool for programmatically generating high-quality terminal screenshots, animated GIFs, and videos using simple script files.
AI Voice Agent Backend
A local-to-cloud bridge for processing Speech-to-Text with Whisper and Text-to-Speech via AWS Polly.
Google Analytics
A comprehensive integration for managing Google Analytics 4 properties and retrieving reporting data via managed OAuth.
METADATA
Featured*
