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

70%

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%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 complete executable code, but it inlines long implementations that duplicate existing bundle scripts without referencing them, and its workflows lack the validation checkpoints expected for batch imaging operations.

Suggestions

Replace the long inline implementations in Core Capabilities with concise summaries plus pointers to the matching scripts/ files (e.g., "See scripts/compute_adc.py for the full implementation") to reduce token weight and surface the bundle.

Restructure Typical Workflows as explicit sequenced steps (load → preprocess → compute → validate → report) with validation checkpoints and error-recovery loops for the batch/segmentation operations.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient prose but inlines seven lengthy code blocks (some 80+ lines) that duplicate executable scripts already shipped in scripts/, making it noticeably heavier than necessary.	3 / 5
Actionability	Every capability section provides fully executable, copy-paste-ready Python with docstrings, arguments, and worked Typical Workflows covering the common cases.	5 / 5
Workflow Clarity	"Typical Workflows" are code-call sequences rather than sequenced multi-step processes, and batch/segmentation operations lack explicit validate→fix→retry checkpoints, which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Sections are well organized, but the scripts/ bundle files (compute_adc.py, cosinor_analysis.py, etc.) are never referenced from the body, so content that should be offloaded remains fully inlined.	3 / 5
	Total	14 / 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 with strong trigger keywords, but it lacks an explicit "Use when..." clause stating when this skill itself should activate, capping completeness. Routing hints reference other libraries rather than this skill's own invocation conditions.

Suggestions

Add an explicit "Use when..." trigger clause listing the natural user scenarios that activate this skill (e.g., "Use when analyzing diffusion MRI, micro-CT bone volumes, hemodynamic waveforms, circadian rhythms, or ciliary beat video").

Frame the pydicom/neurokit2 mentions as complementary routing rather than the only trigger guidance, so the skill's own activation conditions are clear.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete analysis actions ("Diffusion MRI ADC maps, micro-CT bone morphometry, hemodynamic parameter analysis, circadian rhythm cosinor analysis, ciliary beat frequency (FFT), and tissue deformation optical flow") with comprehensive capability coverage.	5 / 5
Completeness	A clear "what" is provided via the enumerated analyses, but there is no explicit "Use when..." trigger clause for this skill; the guideline caps completeness at 3 when such guidance is missing.	3 / 5
Trigger Term Quality	Strong natural-domain keywords are present (circadian rhythm, micro-CT, ciliary beat frequency, DICOM, biosignals), but routing hints ("use pydicom", "use neurokit2") point at adjacent skills rather than this skill's own triggers, leaving a few natural user phrases uncovered.	4 / 5
Distinctiveness Conflict Risk	The specialized clinical/physiological imaging niche with distinct technical triggers (ADC maps, cosinor, CBF via FFT) keeps conflict risk with other skills minimal.	5 / 5
	Total	17 / 20 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: 3a6c3a9

Reviewed: 1 day 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.