structuring-radiology-reports

Converts free-text radiology narratives into structured findings and impression — with measurements, laterality, anatomy, and follow-up recommendations — after OpenMed NER. Use when the user has a CT/MRI/X-ray/ultrasound/mammography report and needs the sections split (technique, comparison, findings, impression), lesion measurements and laterality captured, BI-RADS / Lung-RADS assessment categories pulled, or incidental findings and recommended follow-up tracked. Trigger keywords: radiology report, findings, impression, RadLex, DICOM-SR, BI-RADS, Lung-RADS, ACR, laterality, measurement, nodule, incidental finding, follow-up, structured reporting. Pairs after OpenMed: run openmed.analyze_text on the report (Anatomy/Disease/measurement entities), then assemble structured findings. De-identify the report first. Decision-support only — not a diagnostic medical device.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable body that pairs executable Quick-start code with a clear sequenced workflow and a strong edge-case catalog, all assuming clinical competence. The main gaps are two undefined helper functions in the example code and the absence of an automated validation feedback loop.

Suggestions

Define or inline the _split_findings and _extract_followup helpers (even as brief one-liners) so the Quick-start code is fully copy-paste runnable.

Add an explicit validation checkpoint to the workflow (e.g., verify every structured finding has source_offsets before surfacing) to close the validate→fix→retry loop.

Consider moving the edge-case catalog or the full Quick-start code into a references/ file and summarizing inline, to tighten the SKILL.md body below ~100 lines.

Dimension	Reasoning	Score
Conciseness	Dense and purposeful — it assumes clinical competence and avoids explaining basics — but the Quick-start regex section-splitter and the inline assessment expression are slightly more elaborate than needed inline, keeping it just below fully lean.	4 / 5
Actionability	Provides executable openmed API calls, working regex, and a concrete per-finding schema, but references undefined helpers (_split_findings, _extract_followup), so the code is not fully copy-paste runnable as written.	4 / 5
Workflow Clarity	A clear 7-step numbered workflow with de-identify-first and radiologist-verification guardrails, but verification is framed as human review rather than an automated validate→fix→retry feedback loop.	4 / 5
Progressive Disclosure	Well-organized into labeled sections (When to use, Quick start, Workflow, Hand-off, Edge cases, Standards & references) with external URLs rather than inlined walls of text, but at ~150 lines with no bundle files some inline content (elaborate code, edge-case catalog) could be split into references.	4 / 5
	Total	16 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that crisply states both what it does and when to use it, with comprehensive concrete actions and a rich natural-language trigger keyword list. Its only mild excess is length, but every clause carries load-bearing specificity.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — section splitting (technique/comparison/findings/impression), measurement and laterality capture, BI-RADS/Lung-RADS extraction, and incidental-finding/follow-up tracking — giving comprehensive coverage rather than minor gaps.	5 / 5
Completeness	Explicitly answers 'what' (converts narratives into structured findings/impression with measurements, laterality, anatomy, follow-up) and 'when' (a concrete 'Use when the user has a CT/MRI/X-ray/ultrasound/mammography report and needs…' clause) with concrete trigger phrases.	5 / 5
Trigger Term Quality	An explicit, comprehensive keyword list (radiology report, findings, impression, BI-RADS, Lung-RADS, ACR, laterality, measurement, nodule, incidental finding, follow-up, structured reporting) plus modality terms covers the natural clinical vocabulary users would say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (radiology report structuring scoped to the OpenMed NER pipeline) with distinct RADS/structured-reporting triggers, giving minimal overlap risk with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: maziyarpanahi/openmed
Path: skills/structuring-radiology-reports/SKILL.md
Commit: 80da98c

Reviewed: about 24 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.