HumanAIFusion
Back to Templates
SKILL.mdDatabaseVision & Audio

Medical Image Describer

Generates structured natural language descriptions of radiology images and scans for clinical documentation.

Source File

---
name: medical-image-describer
description: "Generates structured natural language descriptions of radiology images and scans for clinical documentation."
category: "Vision & Audio"
---

# Medical Image Describer

## When to use this skill

Use this skill when you need assistance that generates structured natural language descriptions of radiology images and scans for clinical documentation for Healthcare work.

## Capabilities

- Finding extraction
- Structured report format
- Confidence scoring
- DICOM metadata parsing

## Inputs

Provide the source material, goal, audience, constraints, and preferred output format. Include category-specific context for vision & audio work when available. Share relevant Healthcare policies, terminology, data fields, or review criteria that should guide the result.

## Expected output

Return a clear, review-ready result with the requested structure, assumptions, and any follow-up items called out separately. It should cover: Finding extraction, Structured report format, Confidence scoring, DICOM metadata parsing.

## Guidelines

- Preserve the user's requested tone, audience, and formatting requirements.
- Ask for missing context only when it materially changes the output quality.
- Structure results clearly for review and reuse.
- Call out assumptions, risks, or confidence limitations when the source material is incomplete.