Activity
Mon
Wed
Fri
Sun
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
What is this?
Less
More
3 contributions to Athlete AI Community
Aug 28 • 
Wins
Garmin sync without GitHub
I had some issues with a GitHub automations but I managed to set up an Auto-sync of Garmin activities/wellness data that runs daily in the evening from my local desktop. Set via Windows Task Scheduler (no GitHub), chained straight into an automated run review and feedback report — no manual pulls needed anymore. Claude code set the whole thing up for me. Took some debugging (the PC kept sleeping through the scheduled wake), but I got there within a couple of days!!
0 likes • Aug 29
I asked Claude for a prompt others could use to implement this: I want to schedule [my sync script] to run automatically instead of triggering it manually. It's a Python script (or similar) that pulls data from an API using locally-saved credentials/tokens — not something that can easily run in GitHub Actions or another CI runner, since those start with a clean environment and can't complete auth (password/MFA/token refresh) unattended. Set this up as a local scheduled task (Windows Task Scheduler / cron, depending on OS) instead: 1. Write a small wrapper script that runs the actual sync script and logs its output (stdout+stderr) with a timestamp, to a log file I can check later. Watch for encoding mismatches if mixing native command output with the shell's own log-writing (e.g. PowerShell's Add-Content vs pipe redirection can default to different encodings and produce garbled log text — force a consistent encoding for both). 2. Register the scheduled task to run daily at [time]. If the machine can sleep, explicitly check whether wake timers are enabled and whether the task is set to wake the computer — don't assume it will just work. 3. Actually verify: trigger the task manually first to confirm the wrapper itself works, then leave the real schedule running for several real days and check the log / task history afterward — don't just trust that registering the task means it will fire reliably. A machine that sleeps can silently miss scheduled runs even with wake timers enabled, if it falls back asleep in the gap between waking and the task actually launching. If you see missed days, check the OS's power/sleep event log around the scheduled time to see whether it woke at all, and consider just disabling sleep entirely if this machine is meant to run this kind of automation (most desktops draw negligible extra power idling vs. sleeping). 4. Leave the resulting data-file changes for me to review/commit myself, don't auto-commit unless I ask for that separately.
Aug 22 • 
Wins
Park Run
For anyone into Park Run: There is no Park Run API, so I had claude write script that scrapes my public "all results" page on the parkrun website. I save the results to a local CSV file. Each week, new rows get appended to a local CSV, deduped by run number so re-running the sync never creates duplicates. My dashboard's build step reads that CSV and creates a Park Run page (all-time stats) and renders it — stat tiles, a finish-time trend chart, and a full results table. It's been great for tracking my improvement as I return from an injury. I can share more detailed steps if there is interest
Park Run
1 like • Aug 25
Yes, that's pretty much it. Parkrun is a free, timed 5k event held every Saturday morning in local parks worldwide. If you sign up for a bar code they will track your events and email times afterwards. They are mostly a social outing, but you can push for a good time if you want. Not sure how popular they are in the US, but there are hundreds in places such as UK/Europe/Australia (2,500 events across more than 20 countries worldwide according to Claude)
Garmin only - no Strava or third-party integrations
Kevin, great community that you have established here. I worked through the 7-day challenge but went a bit off-grid, given my starting point was an existing python script that I already had to pull garmin data. Previously I would then paste into an excel file for tracking weekly/monthly totals etc. The Claude code win for me was automating the downloads and building html pages to replicate my old excel file, plus the AI coaching aspect. I have set up a separate database of all my activities that does not rely on any third-party integrations. The AI coaching dashboard is build using this dataset. I have not found any limitations with this method yet, but will be interested if that holds true as I progress.
Garmin only - no Strava or third-party integrations
1-3 of 3
Steve L
2
12 points to level up
@steve-l-3888
Casual runner, engineer, data junkie

Active 11d ago
Joined Jul 16, 2026
Australia
Powered by