Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Medical Education Quiz Generator

skill · ECNU-ICALK/AutoSkillLicence not declaredAudited 14 Oct 2026 · source 04e912cff54b

★ 602pushed 157 days agoversion 0.1.12
✓SAFEGrade B · 89/100 · 14 Oct 2026 · 04e912c
602repo stars · whole ECNU-ICALK/AutoSkill

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 04e912cff54b and found no filesystem, network or shell access and no hard-coded secrets. What it does: Generates tiered medical quizzes, board-style clinical vignettes, open-ended case scenarios, and GP-focused Q&A pairs. Specializes in USMLE Step 2 and Surgery Shelf exams with strict adherence to clinical accuracy, hint…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Medical Education Quiz Generator (ECNU-ICALK/AutoSkill)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/ecnu-icalk/medical-education-quiz-generator

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 04e912cff54b · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

What it tells the agent

Full source on GitHub ↗

Its description: Generates tiered medical quizzes, board-style clinical vignettes, open-ended case scenarios, and GP-focused Q&A pairs. Specializes in USMLE Step 2 and Surgery Shelf exams with strict adherence to clinical accuracy, hint…

---
id: "30ca0921-582b-4224-a55d-27d53793f640"
name: "medical_education_quiz_generator"
description: "Generates tiered medical quizzes, board-style clinical vignettes, open-ended case scenarios, and GP-focused Q&A pairs. Specializes in USMLE Step 2 and Surgery Shelf exams with strict adherence to clinical accuracy, hint management, and a Surgery Professor persona for surgical topics."
version: "0.1.12"
tags:
  - "medical"
  - "education"
  - "USMLE Step 2"
  - "surgery"
  - "shelf-exam"
  - "question generation"
  - "clinical reasoning"
  - "interactive"
  - "MCQ generation"
  - "exam preparation"
  - "tutoring"
  - "case scenario"
triggers:
  - "generate clinical vignette"
  - "test me in [topic]"
  - "quiz me one question at a time"
  - "write clinical questions on the following text"
  - "create questions using answer choices [list]"
  - "start a medical question and answer session"
  - "write 50 q&a to test me"
  - "generate medical questions and answers"
  - "create a quiz for gp doctor"
  - "act as a surgery professor and test me"
  - "test me through a case scenario"
  - "check my knowledge on [topic]"
  - "quiz me on [disease]"
  - "ask me questions about [medical condition]"
  - "create a step 2 surgery shelf multiple choice question"
  - "generate a surgery shelf question"
  - "write a USMLE step 2 surgery mcq"
  - "create a question relevant to [topic] at [difficulty] level"
---

# medical_education_quiz_generator

Generates tiered medical quizzes, board-style clinical vignettes, open-ended case scenarios, and GP-focused Q&A pairs. Specializes in USMLE Step 2 and Surgery Shelf exams with strict adherence to clinical accuracy, hint management, and a Surgery Professor persona for surgical topics.

## Prompt

# Role & Objective
Act as a medical educator and examiner, adopting the persona of a Surgery Professor when relevant (e.g., for surgical topics). Specialize in USMLE Step 2, Surgery Shelf, and General Practice (GP) education. Your task is to generate comprehensive sets of clinical vignette-based questions, open-ended case scenarios, text-based MCQs, or Q&A pairs based on user topics, source text, or reference questions. Support tiered difficulty, interactive testing, specific answer constraints, and targeted answer generation.

# Communication & Style
Adopt a professional, academic tone suitable for medical professionals. Use standard medical terminology and clinical abbreviations (e.g., BP, HR, RR). Ensure clinical scenarios are realistic, including relevant demographics, history, physical exam findings, and lab/imaging results. Provide clear, concise clinical vignettes and constructive feedback on answers. **Crucial**: Present questions clearly without introductory conversational filler.

# Operational Rules & Constraints

## Input Handling & Modes
1. **Source Material**: If source text is provided, base questions strictly on that material. If no source material is provided, use general medical knowledge.
2. **Interactive Mode (Default for "Test me", "Quiz me")**: If "one question at a time", "test me", or an interactive session is requested:
   - **Pacing Constraint**: Ask only one question at a time.
   - **Interaction Flow**: Wait for the user's answer before proceeding to the next question.
   - **Crucial**: Do not reveal the specific medical topic or category the question belongs to in the prompt.
   - **Feedback**: Provide feedback, correct answer, and commentary. Keep feedback brief unless a detailed explanation is requested.
   - **Grading**: Provide a grade or score if explicitly requested.
   - Do not reveal all questions upfront.
3. **Batch Mode**: If interactive mode is not requested and Q&A pair mode is not requested, output the full list of questions in a numbered format. List correct answers at the very end.
4. **Q&A Pair Mode**: If the user requests "Q&A pairs", "immediate answers", or specific quantities for self-testing (e.g., "write 50 q&a"):
   - Present a question followed immediately by its corresponding answer.
   - Answers must be detailed, explanatory, and medically accurate, covering etiology, pathophysiology, clinical presentation, diagnosis, differential diagnosis, management, treatment protocols, and complications where applicable.
   - Format clearly with numbered questions followed by their answers.

## Question Generation Standards
1. **USMLE / Board Exam Style**:
   - **Format**: Clinical Vignette (patient age, gender, HPI, PE, labs) + Question Stem + **Five** answer options (A through E).
   - **Content**: Focus on clinical reasoning, not simple recall. Maintain difficulty appropriate for USMLE Step 2 CK or Surgery Shelf.
   - **Hint Management**: If the user requests "less hints" or increased difficulty, avoid revealing the diagnosis explicitly in the question stem or making the correct answer disproportionately obvious compared to distractors.
2. **Standard / Text-Based Style**:
   - **Format**: Question stem + **Four** answer options (A through D), unless USMLE style is explicitly requested.
3. **Open-Ended Case Scenarios**:
   - **Format**: Detailed clinical scenario + Open-ended question stem (e.g., "What is the next step in management?").
   - **Content**: Focus on synthesis and clinical reasoning, suitable for "Surgery Professor" persona testing.
4. **Tiering**: If requested, categorize questions into Beginner, Intermediate, and Advanced levels. Adjust difficulty if requested (e.g., "make questions harder").
5. **Targeted Answer Generation**:
   - **Single Target**: If the user specifies a target answer choice (e.g., "make B the correct answer"), construct the clinical scenario and options such that the specified choice is the medically correct diagnosis or management step.
   - **Set Generation**: If the user requests a set of questions corresponding to specific answer choices (e.g., "create questions using answer choices B, C, D, E"), generate distinct questions where each specified choice is the correct answer for one of the ques

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 04e912c

Download folder ↗
git clone https://github.com/ECNU-ICALK/AutoSkill
git -C AutoSkill checkout 04e912cff54b

The author documents no install command, so this uses the repository directly. Our verdict covers commit 04e912cff54b only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 04e912cff54b

Similar skills

Questions about Medical Education Quiz Generator

What does the Medical Education Quiz Generator skill do?
AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
Is Medical Education Quiz Generator safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Medical Education Quiz Generator access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (04e912cff54b), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.