| name | apple-health-export-analyzer |
| description | Use when a user wants OpenClaw to analyze Apple Health data either from the Health Data AI Analyzer Mac app or from an Apple Health or HealthKit export.xml with the open-source applehealth repo, verify setup, generate a daily brief, compare recent step and sleep trends, produce a weekly summary, or set up a recurring daily health message. |
Apple Health Export Analyzer
This skill gives OpenClaw two ways to read Apple Health data:
- preferred: use the
Health Data AI Analyzer Mac app if its local API is running
- fallback: use the open-source
applehealth repo with an export.xml
For Mac app mode in restricted OpenClaw sessions, install the companion plugin from the krumjahn/applehealth repo once:
git clone https://github.com/krumjahn/applehealth.git
cd applehealth
python skills/apple-health-export-analyzer/scripts/install_mac_app_companion.py --restart
That installs:
- the
health-analyzer-local OpenClaw plugin
- the
health-analyzer-mac-local companion skill for deterministic localhost access
Use it when the user wants one of these outcomes:
- verify the local setup
- generate a daily brief from recent Apple Health data
- compare steps and sleep over the last 7 days
- produce a weekly summary with workouts and heart rate context
- set up a recurring daily health message with OpenClaw heartbeat or automation
Quick workflow
- First try
--source auto.
- If the Mac app local API is reachable, use that.
- Otherwise use the
applehealth repo plus export.xml.
- Verify setup with
scripts/check_setup.py.
- For a daily brief, use
scripts/daily_brief.py.
- For a 7-day comparison, use
scripts/compare_recent_trends.py.
- For a weekly summary, use
scripts/weekly_summary.py.
If the repo is not in the current workspace, ask the user to clone:
git clone https://github.com/krumjahn/applehealth.git
If needed, read:
Sources
Option 1: Health Data AI Analyzer Mac app
- local API running on the Mac
- app has a saved integration dataset
- no
export.xml needed
- for TUI sessions without local file/shell tools, clone
https://github.com/krumjahn/applehealth, install the companion plugin, and then use health-analyzer-mac-local
- the public skill uses read-only
/openclaw/* localhost endpoints for this mode and does not read local token files
Option 2: applehealth repo
- a cloned
applehealth repo
- an Apple Health
export.xml
Optional:
APPLEHEALTH_REPO environment variable pointing to the repo root--repo, --export, and --out flags for the bundled scripts--source auto|mac-app|export
Core commands
Verify setup
python skills/apple-health-export-analyzer/scripts/check_setup.py --source auto --repo /path/to/applehealth --export /path/to/export.xml --out /path/to/analysis
Daily brief
python skills/apple-health-export-analyzer/scripts/daily_brief.py --source auto --repo /path/to/applehealth --export /path/to/export.xml --out /path/to/analysis --date 2026-03-19
Compare recent trends
python skills/apple-health-export-analyzer/scripts/compare_recent_trends.py --source auto --repo /path/to/applehealth --export /path/to/export.xml --out /path/to/analysis --days 7
Weekly summary
python skills/apple-health-export-analyzer/scripts/weekly_summary.py --source auto --repo /path/to/applehealth --export /path/to/export.xml --out /path/to/analysis --days 7
Response style
When the scripts return JSON:
- summarize it into a concise health brief
- call out missing data explicitly
- give practical suggestions, not medical advice
- do not invent metrics that are absent
For daily brief responses, prefer this structure:
- Status
- What changed
- 3 suggestions
- Missing data
Example output
Status
- Activity was below your recent baseline.
What changed
- Steps: 2,444 vs 7-day baseline 10,005
- Workouts: 0 minutes, 0 workouts
- Sleep: insufficient data
Suggestions
1. Add one easy walk instead of trying to catch up with a hard workout.
2. Use one fixed movement anchor like a walk after lunch.
3. Keep effort moderate when recovery data is missing.
