radiology-image-quiz

Use when creating radiology educational quizzes, preparing board exam questions, or studying medical imaging cases. Generates interactive quizzes with X-ray, CT, MRI, and ultrasound images for medical education.

Quality

67%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/radiology-image-quiz/SKILL.md

Quality

Content

35%

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

The body is undermined by verbatim description repetition, generic template boilerplate, and code examples that do not match the actual packaged script. The reference file is correctly structured one level deep, but overall the content is padded and partly misleading about the real implementation.

Suggestions

Remove the verbatim reprints of the description from 'When to Use' and 'Key Features', and drop the generic template sections (Output Requirements, Response Template, Error Handling, Input Validation) in favor of radiology-specific guidance.

Replace the fabricated RadiologyQuiz API and scripts/radiology_quiz.py CLI examples with the real scripts/main.py interface (generate_quiz(cases) with --demo/--cases), so code examples are copy-paste executable.

Tighten the Quick Check/Audit-Ready section to include a meaningful validation step (e.g. running --demo and confirming the quiz output is well-formed) instead of relying on syntax-only py_compile.

Dimension	Reasoning	Score
Conciseness	The body is padded and verbose: it repeats the frontmatter description verbatim in both 'When to Use' and 'Key Features', and includes generic template sections (Output Requirements, Response Template, Error Handling, Input Validation) that restate process discipline Claude already knows rather than radiology-specific guidance.	1 / 3
Actionability	It offers concrete-looking commands (py_compile, --help) that do run, but the prominent code examples reference an API (RadiologyQuiz.generate/create/create_case/set_difficulty) and a script (scripts/radiology_quiz.py with --modality/--output quiz.pdf) that do not match the actual scripts/main.py, which only exposes generate_quiz(cases) with --demo/--cases.	2 / 3
Workflow Clarity	A sequenced five-step Workflow with a documented fallback path exists, but validation is superficial — py_compile only checks syntax and there is no checkpoint verifying quiz correctness, leaving the validation gaps described by the score-2 anchor.	2 / 3
Progressive Disclosure	A single one-level-deep reference (references/audit-reference.md) is clearly signaled via a markdown link, but the body still inlines large amounts of generic boilerplate that would be better split out, so it stops short of the well-organized score-3 anchor.	2 / 3
	Total	7 / 12 Passed

Description

100%

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 concise, specific, and follows the recommended 'action + Use when...' pattern, explicitly covering both what the skill does and when to invoke it. Trigger terms are natural and the niche is clearly distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('creating radiology educational quizzes, preparing board exam questions, or studying medical imaging cases') plus named modalities ('X-ray, CT, MRI, and ultrasound images'), matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both 'what' ('Generates interactive quizzes with X-ray, CT, MRI, and ultrasound images for medical education') and 'when' via an explicit 'Use when...' trigger clause, so it is not the level below where 'when' is only implied.	3 / 3
Trigger Term Quality	Uses natural terms a medical student or resident would actually say — 'radiology educational quizzes,' 'board exam questions,' 'medical imaging cases,' and the four modality names — giving good coverage rather than jargon.	3 / 3
Distinctiveness Conflict Risk	The radiology-quiz-for-medical-education niche with named modalities and a defined audience is distinct and unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Commit: 7cc5680

Reviewed: 3 days 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.