domains / general / anatomy-quiz-generation / anatomy-quiz-master

anatomy-quiz-master

Skill card

combined

Both copies describe the same anatomy-quiz skill, but the LeoYeAI copy contains the full, coherent procedure (usage boundaries, integration, adaptive engine, common patterns, CLI examples) while the aipoch copy adds a different execution/audit workflow (py_compile, --help, CONFIG block, fallback path) and a truncated description. Neither is a clean superset of the other, so crowning one would hide real alternative steps.

Repositories

Other copies

Combined skill

---
name: anatomy-quiz-master
description: Generate interactive anatomy quizzes for medical education with multiple question types, difficulty levels, and anatomical regions. Supports gross anatomy, neuroanatomy, and clinical correlations for self-assessment and exam preparation.
license: MIT
---

# Anatomy Quiz Master

## When to Use
- Medical students preparing for anatomy practical exams or USMLE Step 1 anatomy questions.
- Self-assessment after lectures or dissections.
- Identifying weak anatomical regions for focused study.
- Creating practice questions for study groups or remediation.
- Teaching assistants generating quiz materials for labs.

## Do NOT Use When
- As the primary learning resource (use textbooks/atlas first).
- As a substitute for cadaver lab attendance.
- For pathology or physiology questions (use specialized skills).
- For board exam registration or scheduling (use official NBME resources).

## Integration
- Upstream: usmle-case-generator, anki-card-creator.
- Downstream: study-limitations-drafter, performance-tracker.

## Core Capabilities

### 1. Regional Anatomy Quizzes
Generate focused quizzes by body region (head/neck, thorax, abdomen, pelvis, upper limb, lower limb, back) with subtopics and question types as documented in the skill references.

```python
from scripts.quiz_generator import QuizGenerator
generator = QuizGenerator()
quiz = generator.generate_quiz(
    region="thorax",
    topics=["heart", "lungs", "mediastinum", "thoracic_wall"],
    difficulty="intermediate",
    n_questions=20
)
quiz.export(format="json", filename="thorax_quiz.json")
```

### 2. Neuroanatomy Pathway Tracing
Generate quizzes for motor, sensory, cranial nerve, reflex, and vascular pathways.

```python
neuro_quiz = generator.generate_neuro_quiz(
    pathway_type="motor",
    include_lesions=True,
    clinical_correlations=True
)
```

### 3. Clinical Correlation Questions
Integrate anatomy with clinical scenarios (surgery, radiology, physical exam).

```python
clinical_quiz = generator.generate_clinical_quiz(
    region="abdomen",
    scenario_types=["surgery", "radiology", "physical_exam"],
    difficulty="advanced"
)
```

### 4. Adaptive Learning System
Track performance and generate personalized quizzes targeting weak areas.

```python
from scripts.adaptive import AdaptiveEngine
engine = AdaptiveEngine()
student_progress = engine.track_performance(
    student_id="student_001",
    quiz_results=results,
    time_per_question=True
)
personalized = engine.generate_adaptive_quiz(
    student_progress=student_progress,
    focus_areas=["thorax_vessels", "cranial_nerves"],
    mastery_threshold=0.80
)
```

## Workflow
1. Confirm the user objective, required inputs, and non-negotiable constraints.
2. Validate that the request matches the documented scope; stop early if unsupported assumptions are required.
3. Use the packaged script path or documented reasoning path with only the inputs that are actually available.
4. Return a structured result separating assumptions, deliverables, risks, and unresolved items.
5. If execution fails or inputs are incomplete, switch to the fallback path and state exactly what blocked full completion.

## Execution and Audit
- Primary implementation surface: `scripts/main.py`.
- Reference guidance: `references/` contains supporting rules, prompts, or checklists.
- Parameters to clarify first: input path, output path, scope filters, thresholds, and domain-specific constraints.
- Output discipline: keep results reproducible, identify assumptions explicitly, and avoid undocumented side effects.

Quick check:
```bash
python -m py_compile scripts/main.py
python scripts/main.py --help
```

## Common Patterns

### Pre-Exam Comprehensive Review
```bash
python scripts/main.py \
  --mode comprehensive \
  --regions all \
  --difficulty intermediate \
  --n-questions 100 \
  --timed \
  --output pre_practice_exam.json
```

### Adaptive Focus on Weak Areas
```bash
python scripts/main.py \
  --mode adaptive \
  --focus abdomen,pelvis \
  --difficulty advanced \
  --n-questions 30 \
  --output adaptive_review.json
```

## Conflicts
- aipoch/medical-research-skills emphasizes a CONFIG block and py_compile/--help audit commands as part of the execution model.
- LeoYeAI/openclaw-master-skills emphasizes CLI mode flags (--mode, --regions, --timed, --output) and upstream/downstream skill integration, without the CONFIG/fallback audit workflow.