Scar image quality review

Skill KangjieShen/openscar-starter/skills/imaging/scar-image-quality-review

AI-native scar and keloid phenotyping framework with registry schema, synthetic mock data, validation scripts, and clinician-reviewable workflow skills

Install

npx -y skills add KangjieShen/openscar-starter --skill scar-image-quality-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Review scar and keloid images for registry usability, comparability limits, privacy status, and OpenScar image quality flags.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.2 KB, as published. Nobody here has run it

Scar Image Quality Review

Description

Use this skill to review scar or keloid images before they enter a registry, report, or before/after comparison workflow. It creates conservative quality flags aligned to the OpenScar image.csv schema. It does not diagnose, measure treatment success, or determine recurrence.

When to Use

Images were captured and need quality-control notes.
A registry entry needs lighting_quality, angle_quality, focus_quality, and privacy_redaction_status.
Before/after images may be confounded by pose, lighting, scale, edema, makeup, or framing.
A team needs to decide whether repeat capture is recommended.

Do Not Use

Do not infer diagnosis from image appearance.
Do not compare treatment outcomes when image quality is inadequate.
Do not approve identifiable images for public use.
Do not edit images to change lesion appearance.

Required Inputs

Image or image description.
Intended use: clinical record, research-deidentified, teaching, or public media.
image_id, visit_id, and lesion_id, if available.
View label, capture distance, device, scale marker, and color reference status if known.

Workflow

Confirm whether the image can be reviewed safely and whether identifiable features are visible.
Identify the view: overview, close_up, oblique, profile, with_scale, or other.
Check technical quality:
- lighting and glare
- camera angle and framing
- focus and motion blur
- scale marker visibility
- color reference visibility
Check comparability:
- same view as prior/future visit
- similar distance and framing
- similar lighting and exposure
- lesion and surrounding normal skin visible
Assign OpenScar quality flags.
List confounders and repeat-capture recommendations.
Produce a registry-ready image.csv row draft when identifiers are available.

Output Format

Image usability summary
OpenScar quality flags
Comparability limitations
Privacy and redaction status
Repeat-capture recommendation
image.csv row draft, if possible

Safety and Compliance

This skill supports documentation, research preparation, and clinician review. It does not diagnose, prescribe, determine recurrence, or replace licensed clinical judgment. Escalate urgent symptoms, suspected infection, wound breakdown, severe pain, rapid progression, bleeding, ulceration, or functional compromise to a qualified clinician.

Do not put real patient images in public repositories. Use secure storage pointers and confirm consent before research, teaching, or public use.

Examples

Review these two anterior chest keloid follow-up images for OpenScar registry quality flags and comparability limitations.

Integration

Works well with scar-photo-standardization, before-after-scar-analysis, scar-registry-entry-builder, and scar-consent-language-review.