anatomy-quiz-master
Generate interactive anatomy quizzes for medical education with multiple.
36
33%
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/anatomy-quiz-master/SKILL.mdQuality
Discovery
32%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 clearly truncated mid-sentence ('with multiple.'), making it incomplete and unprofessional. While it identifies a reasonably specific domain (anatomy quizzes for medical education), it lacks a 'Use when...' clause, comprehensive capability listing, and sufficient trigger terms. The incomplete sentence significantly undermines its utility for skill selection.
Suggestions
Complete the truncated sentence and add a full 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks for anatomy practice, medical quizzes, body system identification, or study aids for medical exams.'
List specific concrete capabilities such as 'Generate multiple-choice questions, label-the-diagram exercises, and timed anatomy identification challenges for medical students.'
Add natural trigger terms users would say, such as 'anatomy practice', 'medical exam prep', 'body parts quiz', 'study flashcards', 'USMLE', or 'gross anatomy review'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (anatomy quizzes, medical education) and one action (generate interactive anatomy quizzes), but the description appears truncated ('with multiple.' ends abruptly) and lacks comprehensive detail about specific capabilities. | 2 / 3 |
Completeness | The description partially addresses 'what' (generate anatomy quizzes) but is clearly truncated and incomplete. There is no 'Use when...' clause or any explicit trigger guidance, and the sentence itself is grammatically incomplete ('with multiple.' trails off). | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'anatomy', 'quizzes', 'medical education', and 'interactive', but is missing common variations users might say such as 'flashcards', 'study', 'exam prep', 'body parts', 'anatomy practice', or specific anatomy terms. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'anatomy' and 'quizzes' provides some distinctiveness, but it could overlap with general quiz-generation skills or broader medical education tools. The truncated description weakens its ability to clearly define its niche. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is excessively verbose and repetitive, with multiple generic boilerplate sections (Error Handling, Input Validation, Response Template, Output Requirements) that add little value for Claude. The domain-specific content (anatomy quiz generation with regions, pathways, clinical correlations) is reasonably well-structured but would benefit greatly from being split across referenced files rather than packed into a single monolithic document. The code examples reference modules that may not exist, reducing actionability.
Suggestions
Remove or drastically compress generic boilerplate sections (Output Requirements, Response Template, Input Validation, Error Handling) — these teach Claude things it already knows and consume significant token budget.
Move detailed content (region tables, clinical scenario examples, quality checklists, common pitfalls) into referenced files in the references/ directory, keeping SKILL.md as a concise overview with navigation links.
Eliminate redundant cross-references like 'See ## Usage above for related details' and 'See ## Workflow above for related details' — these add no information.
Add a concrete validation step in the workflow for verifying quiz output quality (e.g., checking JSON schema, verifying answer key correctness) rather than relying solely on a static checklist.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Contains massive amounts of redundancy (e.g., 'See ## Usage above', 'See ## Workflow above'), boilerplate sections (Output Requirements, Response Template, Input Validation, Error Handling) that teach Claude things it already knows, and repeated information across sections. Dependencies list includes Python stdlib modules (json, random) which is unnecessary. The skill could be reduced to a fraction of its size. | 1 / 3 |
Actionability | Contains Python code examples with specific API calls (QuizGenerator, AdaptiveEngine) and CLI commands with parameters, but these reference modules (scripts/quiz_generator.py, scripts/adaptive.py) whose actual implementations are not provided or verifiable. The code examples look like API documentation for a hypothetical library rather than executable, copy-paste-ready code. The clinical scenario example is concrete and useful. | 2 / 3 |
Workflow Clarity | There is a numbered workflow (steps 1-5) but it is extremely generic and could apply to any skill. The 'Example run plan' provides a more concrete sequence but lacks validation checkpoints beyond py_compile. For a quiz generation tool, there's no explicit validation step to verify quiz quality, anatomical accuracy, or output correctness before delivery. The Quality Checklist is helpful but is a static checklist rather than an integrated workflow checkpoint. | 2 / 3 |
Progressive Disclosure | References to files in references/ and scripts/ directories are clearly listed, which is good. However, no bundle files are provided to verify these exist. The main SKILL.md itself is monolithic — the detailed region tables, code examples, clinical scenarios, and quality checklists could be split into separate reference files. The document has too much inline content that should be in supporting files. | 2 / 3 |
Total | 7 / 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
73f6514
- 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.