Health Guardian

What to check before installing or using this skill: - Review the importer script (scripts/import_health.py) carefully. It uses a hardcoded iCloud export path (~/Library/Mobile Documents/iCloud~com~ifunography~HealthExport/Documents and an AutoSync subfolder) instead of the data_source you are instructed to put in config.json. If your Health Auto Export files live elsewhere, the script may not see them. Modify the script to read config.json or ensure the paths match. - There is no network/telemetry code in the provided files, which matches the README claim that "Nothing leaves your machine." Still, confirm there are no unexpected imports or remote calls before running. - The SKILL.md mentions alert channels (telegram) and scripts/summary.py, but summary.py is missing and no notifier code exists. If you expect alerts to be pushed to Telegram or other channels, you will need to implement that and provide credentials; this skill will just print alerts to stdout by default. - Run the importer/analyzer in a sandbox or with a non-critical test dataset first. Because the importer reads files from your home/iCloud area, test with a copied subset of data to confirm behavior and dedup/merge logic. - Backup existing data/ files before first run; the importer performs atomic writes but will create/modify data/vitals.json. - If you plan to use this with a human under your care, validate the detection thresholds and outputs clinically — this is an assistive tool, not a medical device. - If you want greater assurance, request or locate the upstream repository (package.json points to a GitHub URL) and confirm authorship and recent updates. If you lack the ability to audit the code, avoid providing any external credentials or automating delivery of alerts until the missing notifier functionality and path mismatches are resolved.