← Back to Skills Marketplace
880
Downloads
0
Stars
6
Active Installs
1
Versions
Install in OpenClaw
/install medical-triage
Description
Classify medical messages (emails, iMessages) as critical, urgent, or routine based on medical urgency indicators.
Usage Guidance
This skill appears internally consistent, but note practical and privacy considerations before use: it will classify medical messages but is not a substitute for clinician judgment — route 'critical' items to a human immediately. Because it processes potentially sensitive health information (PHI), ensure your deployment complies with relevant regulations (e.g., HIPAA), logging policies, and data-retention rules. Avoid sending raw PHI to third-party hosted models unless you have proper agreements; consider de-identifying messages or using an internal model. Test extensively with representative examples, set conservative thresholds for automated actions, and keep a human-in-the-loop for any escalation or treatment recommendations.
Capability Analysis
Type: OpenClaw Skill
Name: medical-triage
Version: 1.0.0
The skill bundle is benign. The `SKILL.md` file accurately describes a medical triage classification task and provides standard usage instructions. There are no indications of prompt injection attempts against the AI agent, no requirements for external binaries, no suspicious commands in usage examples, and no evidence of data exfiltration, persistence mechanisms, or other malicious behaviors.
Capability Assessment
Purpose & Capability
Name/description match the instructions: the SKILL.md describes classifying message text into critical/urgent/routine and expects JSON messages as input. No unrelated credentials, binaries, or services are requested.
Instruction Scope
Runtime instructions operate only on supplied message fields (subject, body, date, etc.). They do not instruct reading system files, environment secrets, or sending data to external endpoints beyond the model execution environment.
Install Mechanism
No install spec and no code files — lowest-risk form. The skill is purely instructional and does not pull or extract archives or external binaries.
Credentials
The skill declares no required environment variables, credentials, or config paths; its needs (only message JSON input) are proportionate to the stated function.
Persistence & Privilege
Defaults apply (not always: true). The skill does not request permanent presence or elevated privileges and does not modify other skills' configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install medical-triage - After installation, invoke the skill by name or use
/medical-triage - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the medical-triage skill.
- Classifies medical messages as critical, urgent, or routine based on urgency indicators.
- Uses message content analysis (keywords, symptom severity, patient context, temporal urgency).
- Provides clear input and output JSON formats for easy integration.
- Designed for use with the OpenClaw platform and compatible with programmatic invocation.
Metadata
Frequently Asked Questions
What is Medical Triage?
Classify medical messages (emails, iMessages) as critical, urgent, or routine based on medical urgency indicators. It is an AI Agent Skill for Claude Code / OpenClaw, with 880 downloads so far.
How do I install Medical Triage?
Run "/install medical-triage" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Medical Triage free?
Yes, Medical Triage is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Medical Triage support?
Medical Triage is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Medical Triage?
It is built and maintained by binubmuse (@binubmuse); the current version is v1.0.0.
More Skills