dicom-anonymizer

De-identify DICOM medical images by removing PHI tags for research sharing, with audit logging and study-linkage preservation support.

Quality

75%

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/Other/dicom-anonymizer/SKILL.md

Quality

Content

76%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 content is highly actionable with executable commands and a thorough parameter table, and it is well-structured with real one-level-deep references. Its weaknesses are minor redundancy between output-template sections and the absence of an output-validation feedback loop for a batch/destructive operation.

Suggestions

Add an explicit validation feedback loop in the Workflow (e.g., run anonymization, verify PHI tags were removed via the audit log, re-run or fall back if residual PHI is detected) to lift workflow_clarity above the batch/destructive cap of 3.

Merge the near-duplicate Output Requirements and Response Template sections, and de-duplicate the py_compile line between Quick Check and Audit-Ready Commands, to tighten conciseness.

Reference requirements.txt in the body (e.g., in a Dependencies note) and ensure audit-reference.md adds content beyond the body's command list rather than repeating it.

Dimension	Reasoning	Score
Conciseness	The body is efficient, using tables, code blocks, and bullet lists without over-explaining concepts Claude already knows, though Output Requirements/Response Template and Quick Check/Audit-Ready Commands have minor duplication that could be trimmed.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands (py_compile, --help, smoke_test) plus a complete parameters table and usage examples covering single-file, batch, audit-log, and keep-tags cases.	5 / 5
Workflow Clarity	A clear five-step sequence with fallback and boundary checkpoints is present, but as a batch/destructive skill it lacks an explicit validate-output-then-fix-retry feedback loop, so workflow clarity is capped at 3.	3 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references (phi_tags.json, audit-reference.md) confirmed in the bundle, but requirements.txt is unreferenced and audit-reference.md duplicates body command listings.	4 / 5
	Total	16 / 20 Passed

Description

75%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 and distinctive, naming several concrete capabilities in a clear niche. Its main weakness is the absence of explicit 'when to use' trigger guidance, which caps completeness.

Suggestions

Add a 'Use when...' clause naming concrete trigger phrases (e.g., anonymizing DICOMs, preparing imaging for research sharing, generating PHI audit logs) to lift completeness above 3.

Include the '.dcm' file extension and a synonym like 'de-identify medical imaging' to broaden natural trigger-term coverage.

Keep the existing third-person, action-oriented phrasing — it scores well on specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'De-identify DICOM medical images', 'removing PHI tags', 'audit logging', and 'study-linkage preservation' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	A clear 'what' is present, but there is no 'Use when...' clause or equivalent trigger guidance, so completeness is capped at 3 with 'when' only weakly implied by 'for research sharing'.	3 / 5
Trigger Term Quality	Good natural keyword coverage ('DICOM', 'medical images', 'PHI tags', 'research sharing') but omits common synonyms and file extensions like '.dcm'.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (DICOM de-identification for research) with distinct, domain-specific triggers and minimal overlap with other skills.	5 / 5
	Total	17 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Other/dicom-anonymizer/SKILL.md
Commit: 63c61d3

Reviewed: 4 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.