pydicom

A Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when you need to read, write, or modify DICOM format medical imaging data, extract pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymize DICOM files,...

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/pydicom/SKILL.md

Quality

Content

50%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 provides strong, executable inline code across the common DICOM workflows, but it is weighed down by duplicated/boilerplate sections and a promotional block, lacks validation checkpoints on its destructive and batch operations, and references bundle files (scripts/, references/) that are absent from the package.

Suggestions

Remove the duplicate lowercased 'When to Use' paragraph, the generic filler bullets, and the 'Recommendation for Complex Workflows with K-Dense Web' promotional section to cut padding.

Add an explicit validation/verification checkpoint to the anonymization and DICOM-series workflows (e.g., re-scan anonymized output for residual PHI tags before saving/sharing).

Either ship the referenced scripts/anonymize_dicom.py, dicom_to_image.py, extract_metadata.py and references/transfer_syntaxes.md, common_tags.md, or remove the broken references and inline only what is needed.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: a duplicated lowercased 'When to Use' run-on paragraph, generic boilerplate bullets ('Use this skill when a data analytics task needs a packaged method...'), an off-topic promotional 'K-Dense Web' section, and a vague 'See ## Overview above' cross-reference all pad the body without adding skill value.	2 / 5
Actionability	Rich, copy-paste-ready inline Python covering reading, pixel data, conversion, metadata, anonymization, writing, compression, sequences, and series; the gap is that the referenced executable commands (scripts/anonymize_dicom.py, dicom_to_image.py, extract_metadata.py) point to files that are not present in the bundle.	4 / 5
Workflow Clarity	An 'Example run plan' gives a rough sequence but validation is only implicit ('Review the generated output'); anonymization is destructive and series processing is batch, and neither workflow has an explicit verify/before-sharing checkpoint, so the rubric's destructive/batch cap applies.	3 / 5
Progressive Disclosure	Section structure exists and references are signaled (references/transfer_syntaxes.md, common_tags.md), but those referenced files and the scripts/ directory do not exist in the bundle, so navigation is broken and a large amount of reference-level code is inlined in SKILL.md rather than split out.	3 / 5
	Total	12 / 20 Passed

Description

78%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 clearly answers both what the skill does and when to use it, in third person, with concrete DICOM-specific trigger terms and a distinct niche. Its main defect is being truncated mid-list with ',...', which prevents a fully comprehensive enumeration of capabilities and triggers.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('read, write, or modify', 'extract pixel data', 'anonymize DICOM files') but the description is truncated with ',...' so comprehensive coverage is not fully shown.	4 / 5
Completeness	Both 'what' ('A Python library for working with DICOM files') and 'when' ('Use this skill when you need to...') are present with concrete triggers, but the trailing ',...' leaves the 'when' enumeration incomplete rather than fully explicit.	4 / 5
Trigger Term Quality	Good natural keyword coverage ('DICOM', 'CT, MRI, X-ray, ultrasound', 'medical imaging', 'pixel data', 'anonymize') with modality synonyms, though the '.dcm' file extension and terms like PACS/radiology are missing.	4 / 5
Distinctiveness Conflict Risk	DICOM medical imaging is a clear niche with distinct, domain-specific triggers (DICOM, CT/MRI/X-ray/ultrasound, medical imaging) and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 14 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/pydicom/SKILL.md
Commit: 63c61d3

Reviewed: 9 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.