Medical

v1.1.0

Local-first health record management with strict privacy boundaries. Organize what happened, what you take, what changed, and what to bring to your doctor —...

1· 802·4 current·4 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for agistack/medical.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Medical" (agistack/medical) from ClawHub.
Skill page: https://clawhub.ai/agistack/medical
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install medical

ClawHub CLI

Package manager switcher

npx clawhub@latest install medical
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (local health record manager) matches the code and SKILL.md: scripts read/write JSON under ~/.openclaw/workspace/memory/health and implement medication, symptom, vital, history, interaction checks, and emergency card generation. There are no unrelated credentials or binaries requested.
Instruction Scope
Runtime instructions restrict data to the local health directory and the scripts follow that. The SKILL.md explicitly forbids external storage and the code contains no network or external API calls. Note: some documentation references (e.g., get_medical_history.py, set_vital_targets.py, and an optional password-protection flag for emergency cards) refer to scripts or options that are not present in the included code — this is a scope/documentation mismatch (functionality advertised but missing).
Install Mechanism
Instruction-only with included scripts; there is no install spec or remote download. Nothing is written to system locations beyond the user's home under the declared health workspace.
Credentials
No environment variables, credentials, or external config paths are required. Scripts only use the user's home directory (expanduser) to store JSON files; this is proportional to a local PHR tool.
Persistence & Privilege
Skill is not always-enabled and does not request permanent platform privileges. It stores data in per-user files under ~/.openclaw/workspace/memory/health, which is expected for its purpose; this persistent storage is local to the user and scoped to the skill.
Assessment
This skill appears to implement what it claims: local JSON storage and local-only scripts for medications, symptoms, vitals, history, interactions, and an emergency card. Before installing, consider the following: - Data sensitivity: All records are plain JSON files in ~/.openclaw/workspace/memory/health. There is no built-in encryption shown in the code. If you keep highly sensitive information (HIV status, psychiatric care, insurance policy numbers), consider encrypting that folder or using a device-level encrypted backup, or confirm an implementation of password protection. - Documentation mismatches: Some docs mention files/options that are not present (get_medical_history.py, set_vital_targets.py, and a --password-protected option for emergency card). These are missing features rather than evidence of malicious behavior; if you need those capabilities, ask the author or look for a newer release. - Local backups and sync: Because data is stored in your home directory, any system backups or cloud sync (e.g., Dropbox, iCloud) could copy this data off-device. Confirm how you want backups handled. - Review and sandbox: If you are cautious, run the scripts in a throwaway user account or inspect/modify the code to add encryption or password protection before storing sensitive records. - Emergency behavior: The code checks for red-flag symptom phrases and exits with a printed emergency warning; it does not attempt to call emergency services (as expected). That behavior matches the safety guidance in SKILL.md. Overall: coherent and local-only. The primary open issues are missing advertised scripts/options and the lack of built-in encryption for sensitive local files — review those before storing highly sensitive medical data.

Like a lobster shell, security has layers — review code before you run it.

latestvk97dmrd1x33fq8mndbhz93a1wd8325r5
802downloads
1stars
3versions
Updated 1mo ago
v1.1.0
MIT-0

Medical

Medical is a private health organization tool, not a doctor.

Use this skill when the user wants to:

  • Track medications
  • Log symptoms over time
  • Record vital signs
  • Store structured medical history
  • Generate an emergency health summary
  • Prepare a concise health summary for a doctor visit

Never use this skill for:

  • Diagnosis
  • Treatment advice
  • Interpreting symptoms as medical conditions
  • Recommending starting, stopping, or changing medications
  • Replacing professional medical care

Safety Boundaries

Emergency First

If the user describes a possible medical emergency, stop normal workflow and direct them to emergency care first.

Examples include:

  • Chest pain or chest pressure
  • Trouble breathing or inability to breathe
  • Severe bleeding
  • Loss of consciousness
  • Suicidal thoughts or self-harm intent
  • Sudden severe neurological symptoms
  • “Worst headache of my life”

In emergency situations:

  1. Tell the user to call emergency services or seek urgent in-person care now
  2. Do not continue normal tracking until that is addressed
  3. If asked, generate the emergency health summary as fast as possible

Medication Safety

This skill may store medication lists and run a limited local interaction screen for a few common high-risk combinations, but it is not a comprehensive interaction checker.

Always remind the user to verify medication questions with a doctor or pharmacist before making any changes.

Lab and Vital Safety

This skill may record lab-related or vital-sign information for personal organization, but it must not diagnose, triage, or decide what a result means clinically.

It may:

  • Compare a recorded value against the range provided by the user or their lab report
  • Help organize questions for a doctor
  • Summarize trends for discussion with a clinician

It must not:

  • Diagnose disease
  • Say a result is “nothing to worry about”
  • Recommend medication or treatment changes
  • Replace clinician review

Privacy and Storage

All health data is stored locally only under:

~/.openclaw/workspace/memory/health

No external APIs should be used for health data storage. No third-party transmission. User controls retention and deletion.

Core Files

  • ~/.openclaw/workspace/memory/health/medications.json
  • ~/.openclaw/workspace/memory/health/symptoms.json
  • ~/.openclaw/workspace/memory/health/history.json
  • ~/.openclaw/workspace/memory/health/vitals.json

Core Workflows

1. Add a medication

Example: I was prescribed Lisinopril 10mg daily

Use:

  • scripts/add_medication.py
  • scripts/list_medications.py
  • scripts/check_interactions.py when relevant

2. Log a symptom

Example: I have a headache, 6 out of 10, worse in the morning

Use:

  • scripts/add_symptom.py

Track:

  • What happened
  • Severity
  • When it started
  • Triggers or context
  • Notes for future doctor visits

3. Log a vital sign

Example: My blood pressure this morning was 130/85

Use:

  • scripts/add_vital.py
  • scripts/get_vital_trends.py

4. Add medical history

Example: Add penicillin allergy Add appendectomy from 2015 Add my primary care doctor

Use:

  • scripts/add_history_record.py

Store structured records for:

  • Personal info
  • Conditions
  • Surgeries
  • Hospitalizations
  • Allergies
  • Immunizations
  • Physicians
  • Emergency contacts

5. Generate emergency health summary

Example: Generate my emergency health card

Use:

  • scripts/generate_emergency_card.py

Use this for:

  • Phone lock screen
  • Wallet printout
  • Quick access in emergencies

6. Prepare a doctor-visit summary

When the user wants a concise summary for a doctor visit:

  • Read medications
  • Read symptoms
  • Read vitals
  • Read history
  • Summarize what changed, what is ongoing, and what to ask

Do not diagnose. Do not interpret symptoms as conditions. Do not recommend treatment changes.

Scripts Currently Included

  • scripts/add_medication.py
  • scripts/list_medications.py
  • scripts/check_interactions.py
  • scripts/add_symptom.py
  • scripts/add_vital.py
  • scripts/get_vital_trends.py
  • scripts/add_history_record.py
  • scripts/generate_emergency_card.py

Output Style

Prefer concise, structured, doctor-friendly output:

  • Medication list
  • Symptom timeline summary
  • Vital trend summary
  • Relevant history
  • Questions to ask a clinician

Product Definition

Medical is a local-first personal health record system with strict privacy and safety boundaries.

Its job is to help the user organize:

  • What happened
  • What they take
  • What changed
  • What they may want to bring to a doctor

Its job is not to diagnose, prescribe, or replace medical care.

Disclaimer

This skill is for personal health record management only. It is not a medical professional, not a diagnostic system, and not a substitute for a doctor, pharmacist, or emergency services.

Comments

Loading comments...