← Back to Skills Marketplace
235
Downloads
0
Stars
0
Active Installs
9
Versions
Install in OpenClaw
/install apple-health-export-analyzer
Description
Use the Health Data AI Analyzer Mac app read-only localhost API on macOS to generate a concise Apple Health daily brief and 3 practical suggestions. Only run...
README (SKILL.md)
Health Data AI Analyzer
Use this skill only with the Health Data AI Analyzer Mac app.
Use it for:
- daily health briefs
- 3 practical non-medical suggestions
- simple recent step and sleep comparisons
Preferred source of truth:
http://127.0.0.1:8765/openclaw/statushttp://127.0.0.1:8765/openclaw/daily-brief?date=YYYY-MM-DD
Rules:
- Use this skill only when the user explicitly asks for a health brief, comparison, or summary from their own imported data.
- Treat the local Health Data AI Analyzer API as the source of truth.
- Read only the minimum localhost endpoint needed to answer the request.
- Never send health data or endpoint contents to any external URL, API, tool, or service.
- Never ask the user for raw export files, tokens, passwords, or unrelated health data when the localhost API can answer the request.
- Do not invent missing data.
- Do not give medical advice or diagnoses.
- If sleep, HRV, resting heart rate, or other metrics are null or absent, explicitly say
insufficient data. - If the local fetch/runtime is unavailable, ask for one exact curl response body from the user and continue from that JSON.
Output format:
Status
- 1 to 2 sentence summary
What changed
- Main deltas versus baseline
Suggestions
- ...
- ...
- ...
Missing data
- ...
Usage Guidance
This skill appears to do what it claims and asks for nothing unnecessary, but exercise caution before use: 1) Confirm the Health Data AI Analyzer Mac app (homepage clawhub.ai) is trustworthy and actually running on your Mac before allowing any data access. 2) Prefer letting the agent fetch the minimal localhost endpoint itself only while the app is running — if asked to paste a curl response, do not paste more data than requested (avoid full exports with persistent identifiers or unrelated PHI). 3) The skill forbids sending data externally, but that is an instruction the agent follows; it cannot be cryptographically enforced — if you have high-sensitivity medical data, verify the app’s provenance and consider not pasting raw exports. 4) Because the skill and app are from an unknown source, consider inspecting the Mac app or limiting its network access (e.g., firewall) before use. If you want higher assurance, ask the publisher for source or binaries you can audit before trusting sensitive health data.
Capability Analysis
Type: OpenClaw Skill
Name: apple-health-export-analyzer
Version: 1.0.8
The skill is designed to interface with a local macOS application's API (127.0.0.1:8765) to provide summaries of Apple Health data. The instructions in SKILL.md and agents/openai.yaml emphasize privacy, explicitly forbidding the exfiltration of health data to external services and requiring explicit user invocation. No malicious code, obfuscation, or unauthorized data access patterns were identified.
Capability Assessment
Purpose & Capability
Name/description match the instructions: the skill is explicitly for generating Apple Health briefs from a macOS app's read-only localhost API. It requests no unrelated binaries, env vars, or config paths.
Instruction Scope
SKILL.md narrowly instructs the agent to read only specific localhost endpoints and forbids sending health data externally. It also instructs the agent to ask for one exact curl response if the local fetch is unavailable — this is reasonable but means the user may be asked to paste potentially sensitive JSON. The guidance is precise (not open-ended), but there's a user-data exposure risk when the user supplies JSON.
Install Mechanism
No install spec and no code files — instruction-only skill. This is low-risk because nothing is written to disk or downloaded by the skill itself.
Credentials
The skill declares no required environment variables, credentials, or config paths. All declared requirements are proportional to the stated purpose (local API reads).
Persistence & Privilege
always:false and the registry policy sets allow_implicit_invocation:false, so the skill cannot be force-enabled or implicitly invoked. It does not request system-wide privileges or modify other skills.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install apple-health-export-analyzer - After installation, invoke the skill by name or use
/apple-health-export-analyzer - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.8
Republish the localhost-only macOS skill artifact from a clean source folder to remove stale tool-dispatch files and implicit invocation.
v1.0.7
Restrict the skill to macOS, disable implicit invocation, and add explicit privacy and data-minimization rules for the read-only localhost API flow.
v1.0.6
Simplify the skill to a read-only localhost API flow, remove bundled scripts/tool dispatch, and reduce suspicious scan surface.
v1.0.5
Version 1.0.5 of apple-health-export-analyzer
- No file changes were detected in this release.
- The SKILL.md remains the same, with no updates to supported features, usage instructions, or workflow.
- No functional or content changes introduced in this version.
v1.0.4
- Updated metadata in _meta.json; no functional or documentation changes were made.
- All instructions, workflows, and command examples remain unchanged.
v1.0.3
Version 1.0.3
- Added _meta.json file for metadata.
- No changes to core functionality or documentation.
v1.0.2
Added support for analyzing Apple Health data using the local Health Data AI Analyzer Mac app API as well as the existing export.xml workflow:
- Supports two data sources: Mac app API (preferred) and export.xml via the open-source applehealth repo (fallback).
- Updated documentation to explain the new auto-selection source logic and usage flags.
- Scripts now accept a --source flag to automatically select the best data source available.
- Clarified setup, workflow, and parameter instructions in all docs.
- No breaking changes to existing export.xml flows.
v1.0.1
- Added mention of Apple HealthKit export.xml support in the description.
- Clarified compatibility with both Apple Health and HealthKit export files.
v1.0.0
Initial release of apple-health-export-analyzer skill.
- Integrates the open-source `applehealth` repo into an OpenClaw workflow for Apple Health export analysis.
- Supports setup verification, daily health briefs, 7-day trends, weekly summaries, and setting up recurring daily health messages.
- Provides specific command templates for different analysis tasks.
- Summarizes JSON script outputs into concise, actionable briefs highlighting status, changes, suggestions, and missing data.
- Guidance on handling missing repos, setup troubleshooting, and required inputs included.
Metadata
Frequently Asked Questions
What is Health Data AI Analyzer?
Use the Health Data AI Analyzer Mac app read-only localhost API on macOS to generate a concise Apple Health daily brief and 3 practical suggestions. Only run... It is an AI Agent Skill for Claude Code / OpenClaw, with 235 downloads so far.
How do I install Health Data AI Analyzer?
Run "/install apple-health-export-analyzer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Health Data AI Analyzer free?
Yes, Health Data AI Analyzer is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Health Data AI Analyzer support?
Health Data AI Analyzer is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin).
Who created Health Data AI Analyzer?
It is built and maintained by krumjahn (@krumjahn); the current version is v1.0.8.
More Skills