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.
48
52%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/radiology-image-quiz/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured description with a clear 'Use when' clause and strong trigger terms covering the radiology education domain. Its main weakness is that the 'what it does' portion is somewhat thin—it essentially says 'generates quizzes' without elaborating on specific capabilities like case-based learning, answer explanations, or difficulty progression. The strong domain specificity and natural trigger terms make it highly effective for skill selection despite this limitation.
Suggestions
Expand the capability list with more specific actions, e.g., 'Generates interactive quizzes with case presentations, differential diagnosis challenges, answer explanations, and difficulty levels using X-ray, CT, MRI, and ultrasound images.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (radiology education) and mentions generating interactive quizzes with specific imaging modalities (X-ray, CT, MRI, ultrasound), but doesn't list multiple concrete actions beyond 'generates interactive quizzes'. It lacks detail on what the quizzes contain (e.g., answer explanations, difficulty levels, case presentations). | 2 / 3 |
Completeness | Clearly answers both 'what' (generates interactive quizzes with medical imaging modalities for medical education) and 'when' (creating radiology educational quizzes, preparing board exam questions, studying medical imaging cases) with explicit 'Use when' triggers. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'radiology', 'board exam questions', 'medical imaging', 'X-ray', 'CT', 'MRI', 'ultrasound', 'quiz', 'medical education', 'studying'. These cover a good range of terms a medical student or educator would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining radiology, medical imaging modalities, and educational quiz generation. Very unlikely to conflict with other skills given the specific domain of radiology education and board exam preparation. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is heavily padded with generic boilerplate that has nothing to do with radiology quiz generation. The radiology-specific content (Quick Start, Core Capabilities, CLI Usage) is reasonable but is buried under repetitive, generic sections about input validation, error handling, response templates, and audit commands. The skill contradicts itself on entry points (main.py vs radiology_quiz.py) and references bundle files that don't exist.
Suggestions
Remove all generic boilerplate sections (Output Requirements, Response Template, Input Validation, Error Handling, Implementation Details, Audit-Ready Commands) that don't contain radiology-specific guidance — these waste tokens on things Claude already knows.
Consolidate the entry point: decide whether the script is `scripts/main.py` or `scripts/radiology_quiz.py` and remove all references to the other.
Add a concrete radiology-specific workflow with validation steps, e.g.: 1) Validate image modality matches topic, 2) Generate questions, 3) Verify answer key accuracy, 4) Format output.
Eliminate the duplicated skill description that appears verbatim in 'When to Use' and 'Key Features' sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. The skill description is copy-pasted multiple times (in 'When to Use', 'Key Features'). Generic boilerplate sections like 'Output Requirements', 'Response Template', 'Input Validation', and 'Implementation Details' add significant bloat without radiology-specific value. Many sections repeat the same ideas (e.g., 'Audit-Ready Commands' duplicates 'Quick Check'; 'Workflow' is generic project management steps). Claude already knows how to structure responses and handle errors. | 1 / 3 |
Actionability | The Quick Start and Core Capabilities sections provide concrete Python code examples with specific parameters (modality, difficulty, topic). However, the code references both `scripts/main.py` and `scripts/radiology_quiz.py` inconsistently, and no bundle files are provided to verify these are real. The CLI usage and API examples are reasonably specific but may not be executable given the contradictions. | 2 / 3 |
Workflow Clarity | The 'Workflow' section is entirely generic (confirm objective, validate request, use packaged script, return structured result) with no radiology-specific steps. There are no validation checkpoints for quiz quality, medical accuracy, or image processing. The 'Example run plan' references `scripts/main.py` while the actual quiz code references `scripts/radiology_quiz.py`, creating confusion about the actual execution path. | 1 / 3 |
Progressive Disclosure | The document is a monolithic wall of text with many redundant sections. It references `references/audit-reference.md` and a `references/` directory but no bundle files exist to support these. 'Implementation Details' says 'See ## Workflow above' which is circular. Content that could be separated (error handling, response templates, output requirements) is all inline, and the radiology-specific content is buried among generic boilerplate. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
d3c2c0f
- Reviewed
Table of Contents
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.