Patient enquiry triage

Classifies patient messages into answerable, clinician-handoff, and emergency-escalation buckets.

49|11|Updated Jul 31, 2026
One-click install
npx skills add https://github.com/vstorm-co/agenticos --skill patient-enquiry-triage-vstorm-co
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Patient enquiry triage
Source: https://github.com/vstorm-co/agenticos/tree/main/backend/app/core/catalog/skill_gallery/healthcare/patient-enquiry-triage
Command: npx skills add https://github.com/vstorm-co/agenticos --skill patient-enquiry-triage-vstorm-co

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Healthcare support agents face patient messages that range from harmless administrative questions to clinical emergencies, and answering the wrong one creates real risk. This Skill gives an agent a strict decision framework for which messages it may answer, which must go to a clinician, and which require immediate emergency escalation. ## Core Features & Use Cases - Three-bucket triage: Sorts every incoming message into answer-directly, hand-to-a-person, or stop-and-escalate categories before any reply is drafted. - Document-grounded answers: Administrative answers must cite a source document, with an explicit rule against filling gaps from general knowledge. - Hard safety boundaries: Forbids diagnosing, estimating risk, suggesting doses, or reassuring about symptoms, and mandates giving the local emergency number for red-flag symptoms. - Use Case: A clinic deploys a chat agent on its patient portal. When a patient asks about opening hours, the agent answers from clinic documents; when a patient mentions chest pain, the agent gives the emergency number and ends the exchange. ## Quick Start Use the patient enquiry triage skill to classify this incoming patient message and draft an appropriate response.

Frequently Asked Questions about Patient enquiry triage

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I triage patient messages with an AI agent?▼

Sort each message into one of three buckets before replying: administrative questions the agent can answer from documents, clinical questions handed to a person, and emergencies escalated immediately. The bucket decision determines the entire response.

What patient questions can a chatbot answer safely?▼

A chatbot can answer administrative questions with a documented answer, such as opening hours, what to bring to an appointment, records requests, clinic location, and referral processes. Each answer must cite the source document used.

Can an AI agent answer medication or symptom questions?▼

No. Medication questions, symptom descriptions, results interpretation, and any request to change clinical bookings must be handed to a person immediately. Even reassuring wording like "that sounds normal" counts as a clinical statement and is forbidden.

When should a healthcare chatbot escalate to emergency services?▼

Escalate immediately for chest pain, breathing difficulty, uncontrolled bleeding, suicidal ideation, or a child in distress. Give the emergency number for the country in the record plainly and end the exchange without asking clarifying questions first.

What are the limitations of AI in patient support?▼

The agent must never diagnose, estimate risk, suggest doses, or judge whether a symptom is serious, regardless of how confident the answer feels. If documents do not cover an administrative question, it must say so rather than use general knowledge.