clinical-imaging

Clinical and physiological imaging analysis. Diffusion MRI ADC maps, micro-CT bone morphometry, hemodynamic parameter analysis, circadian rhythm cosinor analysis, ciliary beat frequency (FFT), and tissue deformation optical flow. For DICOM file handling use pydicom; for biosignals use neurokit2.

Quality

73%

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 ./backend/cli/skills/biology/clinical-imaging/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable skill body with complete executable code and good section organization, but it suffers from internal duplication and fails to use the provided scripts/ bundle: full implementations are inlined instead of referenced. Workflow examples also lack explicit validation checkpoints.

Suggestions

Reference the existing scripts/*.py files (e.g., "See scripts/compute_adc.py for the full CLI implementation") instead of inlining every function, which would reduce duplication and improve progressive_disclosure.

Remove the duplicate cosinor example in Quick Start (it repeats section 4 verbatim) or have Quick Start call the packaged function.

Add explicit validation steps to the workflows (e.g., sanity-check ADC values against the 0–3.5e-3 physiological range, verify peak detection counts) to lift workflow_clarity to 3.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient code-focused content, but it is long (~600 lines) with redundancy: the cosinor function appears both in Quick Start and in full in section 4, and the inline implementations largely duplicate the bundled scripts/ files rather than assuming Claude will reuse them.	2 / 3
Actionability	Every capability section provides fully executable, copy-paste-ready Python with concrete imports and a runnable Quick Start and three worked workflows, matching the anchor for fully executable code and specific examples.	3 / 3
Workflow Clarity	The Typical Workflows section lists sequenced examples, but they are single-call sequences without explicit validation checkpoints or feedback loops; the Troubleshooting section gives partial error recovery, so checkpoints remain implicit.	2 / 3
Progressive Disclosure	The body is well-sectioned into seven numbered capabilities, but five scripts/*.py bundle files exist and are never referenced from the body, while their equivalent implementations are inlined — content that should be split out is inline and the bundle is orphaned.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 specific, well-scoped description with strong capability enumeration and good natural trigger terms, but it lacks an explicit "Use when..." trigger clause, which caps completeness. The cross-references to pydicom and neurokit2 helpfully reduce conflict risk with adjacent skills.

Suggestions

Add an explicit trigger clause such as "Use when analyzing diffusion MRI, micro-CT, hemodynamic waveforms, circadian rhythms, ciliary beat, or tissue deformation data" to lift completeness from 2 to 3.

Consider converting the capability nouns into verb-led actions (e.g., "Compute ADC maps", "Quantify bone morphometry") for slightly stronger specificity phrasing.

Dimension	Reasoning	Score
Specificity	The description enumerates six concrete analysis capabilities ("Diffusion MRI ADC maps, micro-CT bone morphometry, hemodynamic parameter analysis, circadian rhythm cosinor analysis, ciliary beat frequency (FFT), and tissue deformation optical flow"), matching the anchor for listing multiple specific concrete actions rather than vague language.	3 / 3
Completeness	It clearly answers "what" with an enumerated capability list, but there is no "Use when..." clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	It includes natural domain terms a specialist user would actually say ("ADC maps", "micro-CT", "DICOM", "circadian rhythm", "biosignals", "ciliary beat frequency"), giving good coverage across the sub-domains rather than generic jargon.	3 / 3
Distinctiveness Conflict Risk	The clinical/physiological imaging niche with named sub-analyses is clearly distinct, and explicitly routing "DICOM file handling" to pydicom and "biosignals" to neurokit2 reduces overlap with neighboring skills.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (610 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/biology/clinical-imaging/SKILL.md
Commit: 52845c3

Reviewed: about 11 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.