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

86%

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

72%

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 well-structured progressive disclosure pointing to real reference and script files. Its main gaps are redundant overview/when-to-use prose and missing validation checkpoints in destructive/batch workflows.

Suggestions

Remove or compress the "Overview" and "When to Use This Skill" sections, which duplicate the frontmatter description, to tighten token efficiency.

Add explicit validation checkpoints to the anonymization workflow (e.g. a verify step that re-scans for residual PHI tags) and the series-processing workflow, turning them into validate→fix→retry loops.

Consolidate the inline "Common Issues and Solutions" troubleshooting into the relevant workflows as inline checkpoints so error recovery is part of the procedure rather than a separate list.

Dimension	Reasoning	Score
Conciseness	The bulk is lean, executable code rather than conceptual padding, but the "Overview" and "When to Use This Skill" sections largely restate the frontmatter description, and the overall body could be tightened without losing clarity.	2 / 3
Actionability	Every section ships complete, copy-paste-ready code with real imports and function calls (e.g. `pydicom.dcmread`, `ds.pixel_array`, `apply_voi_lut`) plus exact CLI invocations for the helper scripts, matching the fully-executable anchor.	3 / 3
Workflow Clarity	Steps appear as sequenced code, but destructive/batch operations like anonymization and multi-slice series processing lack explicit validation checkpoints or validate→fix→retry feedback loops; per the rubric guideline this caps workflow clarity at 2.	2 / 3
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep references — "See `references/transfer_syntaxes.md`", the Helper Scripts and Reference Materials sections — and every referenced path (common_tags.md, transfer_syntaxes.md, and the three scripts) resolves to a real bundle file.	3 / 3
	Total	10 / 12 Passed

Description

100%

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 well-targeted: it states concrete capabilities in third person and gives explicit "Use this skill when" triggers covering the medical-imaging domain. It is a strong, concise description with no notable weaknesses.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — "reading, writing, or modifying medical imaging data", "extracting pixel data", "anonymizing DICOM files", "converting DICOM images to other formats", "handling compressed DICOM data" — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Clearly answers both what ("Python library for working with DICOM files") and when via an explicit "Use this skill when ..." clause plus an "Applies to tasks involving ..." trigger list, matching the highest anchor.	3 / 3
Trigger Term Quality	Covers natural terms users would actually say: "DICOM files", "CT, MRI, X-ray, ultrasound", "PACS systems", "radiology workflows", "healthcare imaging applications" — strong, natural coverage rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	DICOM/medical-imaging is a narrow, clearly bounded niche with distinct triggers (DICOM, PACS, radiology), making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: 52845c3

Reviewed: about 12 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.