pydicom

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.

Quality

80%

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

68%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.

The body is highly actionable with comprehensive executable examples and reasonable file structure, but it is verbose with redundant inline/script duplication and lacks validation checkpoints for its destructive anonymization and batch-processing workflows.

Suggestions

Add explicit validation checkpoints to destructive/batch workflows: after anonymizing, re-open the output with dcmread() and verify no PHI tags remain before sharing; after batch series processing, confirm the saved volume is readable.

Remove redundancy between inline code and helper scripts — point to scripts/anonymize_dicom.py and scripts/dicom_to_image.py instead of duplicating their logic inline, keeping only a minimal illustrative snippet.

Trim 'Key points' callouts and the 'Best Practices' list that restate what the code already shows, to reduce token usage and respect Claude's existing competence.

Dimension	Reasoning	Score
Conciseness	Mostly efficient executable code, but several sections are padded or redundant: inline versions duplicate the helper scripts, 'Key points' restate the code, and the 'Best Practices' list repeats concepts Claude already knows.	3 / 5
Actionability	Provides copy-paste-ready, fully executable code across all common cases (reading, pixel arrays, color/multi-frame, conversion, anonymization, writing from scratch, compression, sequences, series-to-3D-volume) plus explicit script invocation commands.	5 / 5
Workflow Clarity	Steps are sequenced, but destructive/batch operations (anonymization, writing, series processing) lack validation checkpoints or feedback loops; per the rubric, missing validation for destructive/batch work caps this at 3.	3 / 5
Progressive Disclosure	Good structure with a clear overview and one-level-deep references to real files (references/transfer_syntaxes.md, references/common_tags.md) plus a documented scripts/ directory, though reference pointers are sparse and the body still inlines substantial code.	4 / 5
	Total	15 / 20 Passed

Description

92%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.

The description is specific, complete, and uses natural trigger terms with an explicit 'Use when...' clause. Minor gap is the absence of the .dcm extension and a few synonyms that would round out trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the DICOM domain and lists multiple concrete actions ('reading, writing, or modifying', 'extracting pixel data', 'anonymizing DICOM files', 'converting DICOM images', 'handling compressed DICOM data', 'processing medical imaging datasets') for comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (Python library for DICOM with enumerated capabilities) and 'when' ('Use this skill when...', 'Applies to tasks involving...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-keyword coverage ('DICOM files', 'CT, MRI, X-ray, ultrasound', 'anonymizing', 'PACS systems', 'radiology workflows') but missing the .dcm file extension and synonyms like 'medical scans'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (DICOM/medical imaging/PACS) with distinct triggers; the broad 'healthcare imaging applications' tail introduces only minimal overlap risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/pydicom/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.