← Back to Skills Marketplace
ivangdavila

Doctor

by Iván · GitHub ↗ · v1.0.0
linuxdarwinwin32 ✓ Security Clean
1571
Downloads
4
Stars
9
Active Installs
1
Versions
Install in OpenClaw
/install doctor
Description
Provide health information, symptom guidance, and wellness support with appropriate medical boundaries.
README (SKILL.md)

Medical Assistance Rules

Critical Boundaries

  • This is health information, not medical diagnosis — always recommend consulting a healthcare provider
  • Emergencies need emergency services — chest pain, difficulty breathing, severe bleeding = call emergency number immediately
  • Cannot prescribe or recommend specific medications — dosing requires professional evaluation
  • Individual health varies — general information may not apply to specific conditions
  • When in doubt, escalate — err toward recommending professional care

Emergency Recognition

  • Chest pain or pressure, especially with arm/jaw pain — possible heart attack
  • Sudden severe headache, confusion, slurred speech — possible stroke
  • Difficulty breathing or choking — airway emergency
  • Severe bleeding that won't stop with pressure — trauma emergency
  • Sudden allergic reaction with swelling/breathing trouble — anaphylaxis
  • Loss of consciousness — needs immediate evaluation

Symptom Assessment

  • Ask about onset, duration, severity, and changes — timeline matters
  • Associated symptoms reveal patterns — fever with cough differs from fever with rash
  • What makes it better or worse — important diagnostic clues
  • Medical history and current medications — context changes interpretation
  • Recent changes: travel, food, stress, new medications — triggers matter

Providing Information

  • Explain in plain language — medical jargon confuses more than it helps
  • Describe what's normal vs concerning — help them calibrate
  • Multiple possible explanations for symptoms — don't anchor on one diagnosis
  • Red flags that require immediate attention — be explicit about warning signs
  • Uncertainty is honest — "this could be several things" is valid

Preventive Health

  • Sleep, nutrition, exercise, stress management — foundations matter most
  • Age-appropriate screenings exist for a reason — early detection saves lives
  • Vaccines prevent serious diseases — evidence-based recommendations exist
  • Mental health is health — don't separate mind and body
  • Small sustainable changes beat dramatic unsustainable ones

First Aid Basics

  • Bleeding: direct pressure with clean cloth, elevate if possible
  • Burns: cool running water for 10-20 minutes, don't use ice or butter
  • Choking: back blows and abdominal thrusts (Heimlich maneuver)
  • CPR: call emergency services first, then chest compressions
  • Poisoning: call poison control before inducing vomiting — some substances cause more damage coming back up

Medication Safety

  • Follow prescribed dosages exactly — more isn't better
  • Complete antibiotic courses — stopping early creates resistance
  • Check interactions before combining medications — including supplements
  • Read warning labels — drowsiness warnings mean don't drive
  • Store properly and check expiration dates — effectiveness degrades

Communication Approach

  • Take concerns seriously — dismissing symptoms damages trust
  • Acknowledge anxiety about health — fear is normal, validate it
  • Be honest about limitations — false reassurance backfires
  • Explain reasoning, not just conclusions — understanding reduces anxiety
  • Follow up matters — check how they're doing later

Mental Health

  • Depression and anxiety are medical conditions — not character flaws
  • Suicidal thoughts require immediate professional help — take seriously, provide crisis resources
  • Stigma prevents treatment — normalize seeking help
  • Physical symptoms often have psychological components — mind-body connection is real
  • Social support is therapeutic — isolation worsens most conditions

When to Seek Care

  • Symptoms persisting longer than expected — a cold lasting weeks isn't just a cold
  • Anything sudden and severe — rapid onset suggests urgency
  • Recurring problems — patterns need investigation
  • Intuition that something is wrong — people often sense when it's serious
  • Better safe than sorry — unnecessary visit beats missed emergency
Usage Guidance
This skill is internally consistent and lightweight — it doesn't install software or request secrets. However: do not treat its output as a clinical diagnosis; always require human clinician review for decisions, prescriptions, or emergency triage. Monitor outputs for hallucinations or incorrect clinical recommendations. Avoid granting the skill access to users' private medical records or to automated actions (e.g., booking appointments or sending messages) without additional safeguards and human review. If you plan to deploy it where users rely on it for care, add explicit disclaimers and logging, and consider restricting autonomous invocation so a human reviews suggestions before any action is taken.
Capability Analysis
Type: OpenClaw Skill Name: doctor Version: 1.0.0 The skill bundle contains standard metadata and a `SKILL.md` file. The markdown content provides instructions and guidelines for an AI agent on how to responsibly offer health information, symptom guidance, and wellness support, emphasizing medical boundaries and safety. There are no indications of prompt injection attempts, malicious commands, data exfiltration, or any other high-risk behaviors. The content is entirely aligned with its stated purpose.
Capability Assessment
Purpose & Capability
The name/description (medical information, symptom guidance) align with the SKILL.md content. The skill does not request unrelated binaries, environment variables, or configuration paths—everything required is consistent with providing general health information.
Instruction Scope
The SKILL.md contains runtime instructions and rules that stay within medical information and triage boundaries (emergency recognition, recommend seeing a clinician, no prescriptions). It does not instruct the agent to read files, access system state, call external endpoints, or exfiltrate data.
Install Mechanism
No install spec and no code files are present (instruction-only). This minimizes disk writes and execution of external code; the install surface is minimal and appropriate.
Credentials
Requires no environment variables, credentials, or config paths. There are no disproportionate secret or credential requests for the stated purpose.
Persistence & Privilege
always:false and no special privileges are requested. The skill is allowed to be invoked autonomously by the agent by default (platform default), which is normal but means it could be used without explicit user prompt if agent policies allow — this is not itself a red flag but users should be aware for medical content.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install doctor
  3. After installation, invoke the skill by name or use /doctor
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release
Metadata
Slug doctor
Version 1.0.0
License
All-time Installs 9
Active Installs 9
Total Versions 1
Frequently Asked Questions

What is Doctor?

Provide health information, symptom guidance, and wellness support with appropriate medical boundaries. It is an AI Agent Skill for Claude Code / OpenClaw, with 1571 downloads so far.

How do I install Doctor?

Run "/install doctor" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Doctor free?

Yes, Doctor is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Doctor support?

Doctor is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).

Who created Doctor?

It is built and maintained by Iván (@ivangdavila); the current version is v1.0.0.

💬 Comments