anatomy-quiz-master

Generate interactive anatomy quizzes for medical education with multiple.

Quality

57%

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 ./scientific-skills/Academic Writing/anatomy-quiz-master/SKILL.md

Quality

Content

45%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 body mixes genuinely useful domain documentation (Parameters, CLI usage, capability tables) with heavy template boilerplate, duplicated process sections, and broken cross-references ('See ## Usage above' points to a section that appears later). Most critically, the References and Scripts sections promise 14 bundle files of which only 2 exist, so progressive disclosure is largely fictional and the Python examples cannot run.

Suggestions

Fix the bundle mismatch: either add the 8 scripts and 6 reference files the body documents, or rewrite the Scripts/References sections to reflect the actual bundle (main.py, guidelines.md) and remove the non-runnable Python API examples.

Remove template boilerplate and duplication — collapse 'When to Use'/'Key Features'/'Implementation Details'/'Output Requirements' into one concise section, and delete the repeated truncated description.

Repair navigation: the 'Example Usage' and 'Implementation Details' sections say 'See ## Usage/## Workflow above' but those sections appear later in the file; reorder or correct these cross-references and remove the hardcoded '20260318/scientific-skills/...' path.

Dimension	Reasoning	Score
Conciseness	The ~360-line body contains substantial template boilerplate and duplication: the truncated description is repeated verbatim in 'When to Use' and 'Key Features'; 'Key Features'/'Implementation Details'/'Overview'/'Workflow'/'Output Requirements' restate the same generic process language multiple times ('validate the request, choose the packaged workflow, produce a bounded deliverable'). This matches 'noticeably verbose; several unnecessary explanations or padded sections'. Not 1 because there is genuinely useful domain content (Parameters table, capability tables, pitfalls) that is not merely explaining things Claude already knows.	2 / 5
Actionability	The CLI guidance is concrete and executable (`python scripts/main.py --region thorax --difficulty advanced --count 10 --output quiz.json`, a full Parameters table, py_compile checks), but the Python API examples import modules that do not exist in the bundle (`scripts.quiz_generator`, `scripts.adaptive`) and are internally inconsistent with the body's own Scripts listing (`adaptive_engine.py`). The Example Usage section also embeds a non-portable hardcoded path. So guidance is only partly executable — matching 'some concrete guidance but incomplete; missing key details'. Not 4 because a large fraction of the documented capability surface (7 of 8 listed scripts) cannot actually be run.	3 / 5
Workflow Clarity	There is a clear sequence (confirm inputs → validate scope → run packaged script → review output → fallback on failure) with explicit checkpoints: 'Quick Check' runs py_compile before deeper execution, and Error Handling specifies reporting the failure point and a manual fallback — a reasonable validate/recover loop. This fits 'clear sequence with most checkpoints present; minor validation gaps'. Not 5 because the checkpoints are generic template language duplicated across multiple sections (Workflow, run plan, Implementation Details) rather than one tight, operation-specific procedure.	4 / 5
Progressive Disclosure	Scored against the actual bundle: the References section lists 6 files (netter_atlas_correlation.md, terminologia_anatomica.md, usmle_content_outline.md, clinical_correlations.md, image_sources.md, difficulty_calibration.md) and the Scripts section lists 8, but the bundle contains only references/guidelines.md — which the body never mentions — and scripts/main.py. Most referenced paths are dangling, so navigation actively misleads, and large content blocks (quality checklists, pitfalls, capability tables) are inlined that belong in the claimed reference files. This matches 'minimal structure; content that clearly belongs in separate files is inlined'. Not 3 because the problem is not weak signaling of real references — it is that the reference map is mostly fictional.	2 / 5
	Total	11 / 20 Passed

Description

53%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 identifies a clear, distinct niche but is clearly a truncated template artifact: it ends mid-sentence ("with multiple.") and provides no 'Use when...' trigger guidance. It answers 'what' at a basic level and fails to answer 'when'.

Suggestions

Complete the truncated sentence and enumerate the concrete capabilities (e.g., 'Generate interactive anatomy quizzes by body region and difficulty with clinical correlations, adaptive difficulty, and progress tracking').

Add an explicit trigger clause such as 'Use when the user asks for anatomy practice questions, quizzes, USMLE-style anatomy prep, or self-testing on gross/neuroanatomy topics'.

Include natural synonyms users would say — 'anatomy practice questions', 'quiz me on the brachial plexus', 'USMLE anatomy' — to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and one concrete action — "Generate interactive anatomy quizzes for medical education" — but lists no specific capabilities (regions, question types, difficulty levels, exports), matching the 'domain and 1-2 concrete actions, not comprehensive' anchor. Not 4 because the sentence then trails off into a dangling fragment ("with multiple."), so there is no list of several specific actions.	3 / 5
Completeness	The 'what' is clear (generates interactive anatomy quizzes for medical education) but there is no 'Use when...' clause or equivalent trigger guidance anywhere, which caps completeness at 3 per the judging guidelines. The text is also truncated mid-sentence ("with multiple."), leaving the 'what' itself incomplete; not 4 because the 'when' is entirely absent rather than just under-specified.	3 / 5
Trigger Term Quality	It contains relevant natural keywords like "anatomy quizzes" and "medical education", but misses common variations a user would actually say: "anatomy practice questions", "quiz me on", "USMLE", "neuroanatomy". Fits the 'some relevant keywords but missing common variations or synonyms' anchor; not 4 because coverage of natural phrasings is thin for this domain.	3 / 5
Distinctiveness Conflict Risk	Anatomy quiz generation for medical education is a clear niche with low overlap risk against generic quiz, tutoring, or document skills. Not 5 because the anchor example pairs a distinct niche with explicit trigger phrases, and this description offers none — leaving minor overlap risk with general medical-education or study-help skills.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Academic Writing/anatomy-quiz-master/SKILL.md
Commit: 686e09d

Reviewed: 12 hours 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.