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

66%

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

61%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.

A highly actionable, well-sectioned body whose code is executable and unit-aware, but it functions as a monolith: it duplicates its own examples, lacks validation checkpoints in batch imaging workflows, and completely ignores the scripts/ bundle it ships with.

Suggestions

Replace the inlined implementations with short usage snippets and one-level-deep pointers to the existing scripts (e.g., "**ADC maps**: See [scripts/compute_adc.py](scripts/compute_adc.py) for the full CLI implementation"), cutting SKILL.md to an overview.

Add validation checkpoints to the workflows (e.g., visually verify the Otsu bone mask or ADC map against the source volume before reporting statistics, and re-check if the mask includes soft tissue).

Remove the duplicated cosinor example — keep it in either Quick Start or section 4, and have Workflow 3 reference that instead of repeating it.

Dimension	Reasoning	Score
Conciseness	The prose is lean, but the body duplicates itself: the Quick Start re-implements the cosinor example that appears again in section 4 and a third time in Workflow 3, and Workflow 1 just re-invokes section 1's function. It matches the 3 anchor (mostly efficient but could be tightened); not 4 because the redundant example blocks are clearly trimmable.	3 / 5
Actionability	Every capability ships as a complete, executable function with real defaults, docstrings, units, and printed outputs (e.g., compute_adc_map, bone_morphometry with voxel_size_um, cosinor_analysis with significance testing), plus an install command — copy-paste ready and covering the common cases. Only cosmetic warts (an unused idx loop variable) keep it from being flawless, which the 5 anchor does not penalize.	5 / 5
Workflow Clarity	"Typical Workflows" are single unvalidated calls (load → analyze → print) with no verification of intermediate results (e.g., inspect the segmentation before reporting BV/TV or plaque counts). These are batch analyses over whole volumes/stacks, and the Troubleshooting section only partially compensates as an error-recovery loop, so the batch-operation cap of 3 applies.	3 / 5
Progressive Disclosure	The bundle contains five standalone scripts (compute_adc.py, cosinor_analysis.py, etc.) that duplicate the body's code, yet the ~600-line SKILL.md never references any of them — all seven full implementations are inlined and the bundle is undiscoverable. This matches the 2 anchor (content that clearly belongs in separate files is inlined; references buried), not 3, because no reference to the bundle exists at all.	2 / 5
	Total	13 / 20 Passed

Description

71%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.

A specific, capability-rich description in third-person voice with good natural trigger terms and explicit deflection to sibling skills. Its main weakness is the complete absence of a "Use when..." trigger clause, which caps completeness, and some missing synonyms/file extensions.

Suggestions

Append an explicit trigger clause, e.g.: "Use when analyzing diffusion MRI, micro-CT volumes, blood pressure waveforms, circadian time series, high-speed ciliary video, or fluorescence plaque images."

Add natural synonyms and file extensions users would mention: ".nii"/"NIfTI", "DWI", "apparent diffusion coefficient", "trabecular bone", ".dcm".

Sharpen the opening beyond the broad "Clinical and physiological imaging analysis" (e.g., "Quantitative analysis of clinical and physiological imaging and biosignal data") to reduce overlap with a general bioimage-analysis skill.

Dimension	Reasoning	Score
Specificity	The description enumerates six concrete, named capabilities with their techniques — "Diffusion MRI ADC maps, micro-CT bone morphometry, hemodynamic parameter analysis, circadian rhythm cosinor analysis, ciliary beat frequency (FFT), and tissue deformation optical flow" — which matches the 5 anchor (multiple specific concrete actions, comprehensive coverage). It is not 4 because there is no meaningful coverage gap, and it uses third-person descriptive voice throughout.	5 / 5
Completeness	The "what" is clear and comprehensive (the capability list), but there is no "Use when..." clause or equivalent trigger guidance — the final sentence ("For DICOM file handling use pydicom; for biosignals use neurokit2") is deferral guidance, not usage triggers, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Good natural keyword coverage: "Diffusion MRI", "ADC", "micro-CT", "circadian rhythm", "ciliary beat frequency", "DICOM", "biosignals" are phrases users would actually say. It is not 5 because common synonyms and file extensions are missing (".nii"/"DWI", "apparent diffusion coefficient" spelled out, "trabecular"/"bone microarchitecture", ".dcm").	4 / 5
Distinctiveness Conflict Risk	The specialized clinical-imaging niche (cosinor, ciliary beat frequency, bone morphometry, ADC) is largely distinct, and the explicit deflections to pydicom and neurokit2 reduce conflict risk. It is not 5 because the broad opening phrase "Clinical and physiological imaging analysis" still overlaps a general bioimage-analysis skill.	4 / 5
	Total	16 / 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: 4082a2e

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.