Clinical Risk Prediction

When assessing clinical risk, follow these steps:

1. Extract relevant risk factors

Identify information that may influence risk, including:

• Symptoms (severity, duration)
• Vital signs and clinical findings
• Medical history (e.g., chronic conditions)
• Age or vulnerability indicators
• Laboratory or exam results

Only use explicitly stated information.

2. Identify risk indicators

Determine whether the case includes signs of:

• Clinical deterioration
• Severity or acute conditions
• Comorbidities that increase risk
• Abnormal findings or critical values

Do not assume missing data.

3. Assign risk level

Classify the case into one of the following:

• LOW
• MODERATE
• HIGH

Base the classification strictly on the available information.

4. Justify the classification

Provide a brief explanation including:

• Key risk factors identified
• Why they increase or decrease risk

Keep justification concise and grounded in the input.

5. Express uncertainty

• If information is incomplete, state uncertainty
• Avoid overconfidence

6. Output format

Return the result as structured text:

Risk Level: HIGH

Rationale:
- ...
- ...

7. Constraints

• This is assistive risk assessment, not a medical diagnosis
• Do not provide treatment recommendations
• Do not hallucinate clinical information
• Do not infer missing data
• Do not express certainty beyond the available evidence

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: elisaterumi-ai
• Source: elisaterumi-ai/clinical-agent-skills
• License: Apache-2.0

Install and usage instructions live in the source repository linked above.