anatomy-quiz-master

Generate interactive anatomy quizzes for medical education with multiple.

Quality

46%

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/anatomy-quiz-master/SKILL.md

Quality

Content

42%

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

The content surface is rich and well-structured on paper, but it is padded with generic boilerplate and critically references 13 bundle files that do not exist, undermining both executability and navigation.

Suggestions

Either create the referenced files (quiz_generator.py, adaptive_engine.py, terminologia_anatomica.md, etc.) or remove the dangling references so signaled navigation resolves to real files.

Strip the generic templated sections (Output Requirements, Response Template, Input Validation, Error Handling) or collapse them into a concise block, keeping only anatomy-quiz-specific guidance.

Replace the non-runnable imports with the actual scripts/main.py CLI interface so the code examples are executable against the real bundle.

Dimension	Reasoning	Score
Conciseness	Real content exists (code examples, parameter table, quality checklist, pitfalls) but the ~365-line body is padded with generic templated boilerplate (Output Requirements, Response Template, Input Validation, Error Handling) and redundant cross-references ("See ## Usage above", "See ## Workflow above") that could be tightened.	2 / 3
Actionability	Examples look concrete (QuizGenerator, AdaptiveEngine, a parameter table, CLI commands) but the code imports modules that do not exist in the bundle (scripts.quiz_generator, scripts.adaptive) and references API methods with no backing implementation, so the code is not actually executable as written.	2 / 3
Workflow Clarity	A sequenced Workflow and an Example run plan are present with a basic validation checkpoint (py_compile, --help) and a fallback path, but the workflow is generic boilerplate not tied to the anatomy-quiz task and lacks task-specific validation checkpoints.	2 / 3
Progressive Disclosure	The body is a monolithic wall of text and signals one-level-deep references to 6 reference files and 7 scripts, but the actual bundle contains only references/guidelines.md and scripts/main.py, so the signaled navigation points to non-existent files.	1 / 3
	Total	7 / 12 Passed

Description

50%

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 real niche but is truncated ("with multiple.") and omits any explicit use-when trigger, leaving it informative yet incomplete and only modestly distinctive.

Suggestions

Complete the truncated sentence and enumerate concrete capabilities, e.g. question types and adaptive difficulty, instead of ending at "with multiple."

Add an explicit trigger clause such as "Use when creating anatomy practice questions, USMLE-style quizzes, or regional anatomy review for medical education."

Include natural user terms like "USMLE", "anatomy practice", and "medical students" to improve trigger coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names a concrete action and domain ("Generate interactive anatomy quizzes for medical education") but the sentence is truncated mid-phrase ("with multiple.") and lists no further actions, so it is not comprehensive.	2 / 3
Completeness	Answers "what" (generate interactive anatomy quizzes for medical education) but provides no "Use when..." clause or explicit trigger guidance; per the rubric a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Includes some natural terms a user might say ("anatomy quizzes", "medical education") but is missing common variations like "USMLE", "medical students", or "anatomy practice", and the truncated tail adds no usable keyword.	2 / 3
Distinctiveness Conflict Risk	The anatomy-quiz niche is somewhat specific, but the broken description and absence of trigger guidance leave it overlapping with broader quiz or medical-education skills rather than a clearly distinct trigger set.	2 / 3
	Total	8 / 12 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
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.