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

The canonical home for this skill is pydicom in K-Dense-AI/scientific-agent-skills

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.

A thorough, highly actionable reference with executable examples and well-organized references to real bundle files, but it runs long and its destructive workflows (notably anonymization) lack embedded validation checkpoints.

Suggestions

Add an explicit validation step to the anonymization workflow (e.g., re-read the output and confirm PHI tags are absent or run a verification script) to satisfy the destructive-operation feedback-loop requirement.

Trim or move the multi-frame, color-space, and write-from-scratch examples into references/ to reduce inline length and improve conciseness.

Consolidate the 'Common Issues and Solutions' and 'Best Practices' sections or move them to a reference file to tighten the core SKILL.md body.

Dimension	Reasoning	Score
Conciseness	The ~425-line body is mostly efficient with brief intros and code-focused sections, but the color-image, multi-frame, and from-scratch writing examples plus separate 'Common Issues', 'Best Practices', and 'Documentation' sections add length that could be tightened or pushed to references.	3 / 5
Actionability	Fully executable, copy-paste-ready code blocks cover the common cases (reading, pixel extraction, conversion, metadata modification, anonymization, writing, compression, sequences, series) plus concrete script invocation commands like 'python scripts/anonymize_dicom.py input.dcm output.dcm'.	5 / 5
Workflow Clarity	Sections are sequenced by task but lack explicit validation checkpoints or feedback loops; anonymization is a destructive operation whose workflow has no validate/verify step embedded in the flow, capping this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	Good structure with a concise overview and clearly signaled one-level-deep references to real bundle files (references/common_tags.md, references/transfer_syntaxes.md) and the scripts/ directory; minor organization gaps where some inline material could live in references.	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.

A strong, well-structured description that concretely states what the skill does and when to use it with natural trigger terms, using proper third-person voice throughout. Only minor gap is the absence of the .dcm file extension among trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—'reading, writing, or modifying', 'extracting pixel data', 'anonymizing DICOM files', 'converting DICOM images to other formats', 'handling compressed DICOM data'—with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' ('Python library for working with DICOM files') and 'when' ('Use this skill when reading, writing, or modifying...'; 'Applies to tasks involving medical image analysis, PACS systems, radiology workflows') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural keywords ('CT, MRI, X-ray, ultrasound', 'PACS systems', 'radiology workflows') that users would say, but lacks the '.dcm' file extension and a few common synonyms, keeping it just below a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (DICOM medical imaging) with distinct triggers like 'PACS systems' and 'radiology workflows', making conflict with other skills minimal.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/biology/pydicom/SKILL.md
Commit: 3a6c3a9

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.