OpenParable
Skip to content
← Back to skills

Apple Health Export Analyzer

Apps & Automation
apple-health-export-analyzer

Apple Health Export Analyzer is an Agent Skill for apps & automation published in the krumjahn/applehealth repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

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.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/krumjahn/applehealth/blob/HEAD/skills/apple-health-export-analyzer/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/apple-health-export-analyzer, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

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

  1. First try --source auto.
  2. If the Mac app local API is reachable, use that.
  3. Otherwise use the applehealth repo plus export.xml.
  4. Verify setup with scripts/check_setup.py.
  5. For a daily brief, use scripts/daily_brief.py.
  6. For a 7-day comparison, use scripts/compare_recent_trends.py.
  7. 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.