CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

38%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 core pydicom workflows (reading, pixel data, writing, compressing, series handling) are technically sound and copy-paste executable, but the file is undermined by heavy boilerplate padding, duplicated sections, embedded advertising, and — most seriously — a claimed bundle of scripts and references that does not exist in the repository. Validation steps for destructive anonymization are also missing.

Suggestions

Ship the referenced bundle or remove the dead paths: either add `scripts/anonymize_dicom.py`, `scripts/dicom_to_image.py`, `scripts/extract_metadata.py`, `references/common_tags.md`, and `references/transfer_syntaxes.md`, or delete all sections that reference them.

Cut the auto-generated boilerplate ('Key Features', 'Implementation Details', duplicated 'When to Use', the K-Dense Web recommendation) — roughly 60 lines of the body add no task value and duplicate the frontmatter description.

Add an explicit validation checkpoint to the anonymization workflow (e.g., a command or short code block that re-reads the output and asserts PHI tags are empty) since it is a destructive batch operation on medical data.

DimensionReasoningScore

Conciseness

The ~490-line body has several padded or unnecessary sections: a duplicated trigger list ("When to Use" restating the frontmatter in lowercase, then "When to Use This Skill" again), auto-generated boilerplate ("Execution model: validate the request, choose the packaged workflow...", "Packaged executable path(s)... plus 2 additional script(s)"), a dead pointer ("See `## Overview` above for related details" under Implementation Details), and an off-topic promotional section recommending K-Dense Web. This matches anchor 2's 'several unnecessary explanations or padded sections'.

2 / 5

Actionability

The inline Python examples (dcmread, pixel_array, writing files, sequences, series sorting) are concrete and executable, matching anchor 4 — but key commands are broken: `python scripts/anonymize_dicom.py --help`, `python scripts/dicom_to_image.py input.dcm output.png`, and `python scripts/extract_metadata.py file.dcm` reference scripts that do not exist in the bundle, and the Example Usage block starts with `cd "20260316/scientific-skills/..."`, an environment-specific path. Missing key executable surfaces pulls this to anchor 3.

3 / 5

Workflow Clarity

An 'Example run plan' with 4 steps and an Input Validation section provide a rough sequence, but anonymization — a destructive, PHI-removing batch operation — has no validation checkpoint (no command to verify PHI removal, e.g., re-scanning output for identifying tags; Best Practice #7 says 'thoroughly validate anonymization' but no step implements it). Per the rubric cap for destructive/batch operations without validation, this cannot exceed 3.

3 / 5

Progressive Disclosure

The body claims a bundle that does not exist: `references/common_tags.md`, `references/transfer_syntaxes.md`, and three scripts under `scripts/` are all absent, so every signaled reference is a dead path and navigation fails. Combined with long inline API-style reference content (transfer syntax lists, full common-tag-style examples) that should live in separate files, this sits at anchor 2 ('content that clearly belongs in separate files is inlined') rather than 3, since the references present are not merely unsignaled but nonexistent.

2 / 5

Total

10

/

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 is strong: domain-specific, action-oriented, and explicitly pairing a "what" with a "Use this skill when..." trigger clause. Its one real defect is that the text is truncated with a literal "..." right after "anonymize DICOM files,", cutting off the rest of the capability list.

Suggestions

Complete the truncated description — replace the trailing '...' with the full capability list (convert DICOM images to other formats, handle compressed DICOM data, process metadata and tags, work with medical imaging datasets) so the 'when' guidance is fully stated.

Add the '.dcm' file extension and common synonyms (e.g., 'medical imaging datasets', 'PACS') to broaden natural trigger coverage.

Tighten the wording to third-person library voice ('Reads, writes, and modifies DICOM files...') to reduce filler like 'Use this skill when' repetition.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "read, write, or modify DICOM format medical imaging data, extract pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymize DICOM files" — matching the 'several specific actions with minor gaps' anchor. It falls short of 5 because the description is literally truncated with a trailing "...", so the full action coverage (converting formats, handling compressed data, processing tags) is cut off and not verifiable from the description itself.

4 / 5

Completeness

It answers both "what" ("A Python library for working with DICOM... files") and "when" ("Use this skill when you need to read, write, or modify...") with concrete trigger phrases, which normally maps to anchor 5. However, the "when" clause is cut off mid-list by the literal "...", leaving the trigger guidance incomplete — closer to anchor 4's "'when' could be more explicit or specific" than a fully complete answer.

4 / 5

Trigger Term Quality

Good keyword coverage: "DICOM", "medical imaging data", "CT, MRI, X-ray, ultrasound", "pixel data", "anonymize" are natural terms users would say. It misses a few natural variations such as the ".dcm" file extension and phrases like "medical imaging datasets", and the truncation hides any further synonyms, so it fits anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

"DICOM" and "medical imaging data" (CT, MRI, X-ray, ultrasound) define a clear niche with distinct trigger terms and minimal overlap with other document/image skills. Unlike anchor 4's "Works with PDF and Word document files", no sibling skill is likely to fire on these triggers.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.