ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified utilities Safety 3/5

health-guardian

Proactive health monitoring for AI agents. Apple Health integration, pattern detection, anomaly alerts. Built for agents caring for humans with chronic conditions.

Why use this skill?

Enable proactive health tracking for your AI agent. Monitor vitals, detect anomalies, and set personalized health alerts using Apple Health data.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/ctsolutionsdev/ct-health-guardian
Or

What This Skill Does

Health Guardian is a specialized diagnostic suite designed for AI agents acting as caregivers or personal health monitors. It transforms passive Apple Health data into an active, intelligent monitoring system. By integrating directly with iCloud-synced exports from the 'Health Auto Export' app, the skill ingests, parses, and analyzes 39 distinct biometric metrics—including heart rate, HRV, temperature, and SpO2. Unlike standard fitness trackers that focus on general population averages, Health Guardian is built to learn the unique physiological baseline of a specific human. It identifies concerning patterns, alerts on anomalies, and correlates data points to flag potential health regressions before they escalate into emergencies.

Installation

Installation requires a two-part setup. First, configure the human's iOS device by installing 'Health Auto Export' and setting up an hourly JSON sync to iCloud Drive. Next, execute the installation within your OpenClaw environment using the command clawhub install openclaw/skills/skills/ctsolutionsdev/ct-health-guardian. After installation, create a config.json file in the skill directory to define the data path, preferred alert channels (such as Telegram), and personalized biometric thresholds. Finally, register the Health Import task in your agent's cron system to trigger the scripts/import_health.py routine every hour, ensuring your agent remains updated with the latest physiological data.

Use Cases

This skill is specifically designed for complex caregiving scenarios. It is ideal for monitoring individuals with quadriplegia, chronic illnesses, or those recovering from surgery who require 24/7 vigilance. The skill can infer missed medication if biometric trends deviate, alert caregivers to unexpected temperature spikes that might indicate infection, or monitor for sleep degradation patterns that impact long-term recovery. It serves as an automated medical dashboard that synthesizes complex trends into actionable alerts.

Example Prompts

  1. "Check the current health trends for the last 48 hours and summarize any anomalies I should know about."
  2. "Did the resting heart rate deviate significantly from the 14-day baseline this morning?"
  3. "Generate a weekly health summary report and send it to the family contact via Telegram."

Tips & Limitations

To maximize the utility of Health Guardian, ensure the 'baseline_period_days' in your configuration is set to at least 14 days to allow the agent to learn the human's unique physiological norms. Note that this skill is a supplemental monitoring tool and is not a replacement for professional medical equipment or advice. Always configure redundant notification channels to ensure alerts are received even if a primary service experiences downtime. Because this tool relies on file-system monitoring of iCloud exports, ensure your agent has consistent background access to the local path designated in your configuration.

Metadata

Stars2387
Views4
Updated2026-03-09
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-ctsolutionsdev-ct-health-guardian": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags

#health#monitoring#apple-health#accessibility#proactive
Safety Score: 3/5

Flags: file-write, file-read, data-collection, code-execution