Check UnderstandingSAFE

Learn AI Engineering! Learn it. Build it. Ship it for others.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: check-understanding
version: 1.0.0
description: Phase quiz for AI Engineering from Scratch. Trigger with "quiz me", "test phase", "check my understanding", "do I know phase 3", or `/check-understanding <phase>`.
---

# Check Understanding

Test your knowledge of a completed phase from the AI Engineering from Scratch course.

## Activation

This skill activates when the user says things like:
- `/check-understanding 3` or `/check-understanding deep-learning`
- "quiz me on phase 2"
- "test phase 1"
- "check my understanding of transformers"
- "do I know phase 3"
- "am I ready for the next phase"

## Input

Accepts a phase number (0-19) or a phase name as argument. If no argument is provided, ask the user which phase they want to be tested on by listing all 20 phases.

## Phase Map

Map the argument to the correct phase directory under `phases/`:

| Input | Directory | Phase Name |
|-------|-----------|------------|
| 0, setup, tooling | `00-setup-and-tooling` | Setup & Tooling |
| 1, math, math-foundations | `01-math-foundations` | Math Foundations |
| 2, ml, ml-fundamentals | `02-ml-fundamentals` | ML Fundamentals |
| 3, deep-learning, dl | `03-deep-learning-core` | Deep Learning Core |
| 4, cv, computer-vision, vision | `04-computer-vision` | Computer Vision |
| 5, nlp | `05-nlp-foundations-to-advanced` | NLP -- Foundations to Advanced |
| 6, speech, audio | `06-speech-and-audio` | Speech & Audio |
| 7, transformers | `07-transformers-deep-dive` | Transformers Deep Dive |
| 8, generative, gen-ai, genai | `08-generative-ai` | Generative AI |
| 9, rl, reinforcement-learning | `09-reinforcement-learning` | Reinforcement Learning |
| 10, llms, llm, llms-from-scratch | `10-llms-from-scratch` | LLMs from Scratch |
| 11, llm-engineering, llm-eng | `11-llm-engineering` | LLM Engineering |
| 12, multimodal | `12-multimodal-ai` | Multimodal AI |
| 13, tools, protocols, mcp | `13-tools-and-protocols` | Tools & Protocols |
| 14, agents, agent-engineering | `14-agent-engineering` | Agent Engineering |
| 15, autonomous | `15-autonomous-systems` | Autonomous Systems |
| 16, multi-agent, swarms | `16-multi-agent-and-swarms` | Multi-Agent & Swarms |
| 17, infrastructure, production, infra | `17-infrastructure-and-production` | Infrastructure & Production |
| 18, ethics, safety, alignment | `18-ethics-safety-alignment` | Ethics, Safety & Alignment |
| 19, capstone, projects | `19-capstone-projects` | Capstone Projects |

## Procedure

### Step 1: Resolve the Phase

Parse the argument. If it is a number, validate it is between 0 and 19 inclusive. If the number is out of range, tell the user: "Phase [N] does not exist. Valid phases are 0-19." and show the full list for them to pick from. If it is a name or keyword, look it up in the Phase Map above. If the keyword does not match any entry in the map, tell the user: "Unknown phase '[keyword]'. Pick from the list below:" and present all 20 phases. If no argument is provided, ask the user to pick from the full list.

### Step 2: Read the Phase Content

If the repo is cloned (a `phases/` directory exists in or above the current directory), find all lesson directories under `phases/<phase-dir>/` and read each lesson's `docs/en.md`. If it is not cloned, get the phase's lesson list from the Contents section of the README (fetch `https://raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/main/README.md`), then fetch each lesson's `docs/en.md` from the same raw base URL. These documents contain the teaching material you will generate questions from.

Read as many lesson docs as needed to cover the full breadth of the phase. If a phase has many lessons (15+), prioritize reading a representative spread: first few, middle, and last few.

### Step 3: Generate 8 Questions

Create exactly 8 multiple-choice questions drawn from the lesson content you just read:

**Questions 1-4: Conceptual (What/Why)**
These test understanding of ideas, definitions, and reasoning. Examples:
- "What is the purpose of X?"
- "Why does Y happen when Z?"
- "Which statement best describes the relationship between A and B?"
- "What problem does X solve?"

**Questions 5-8: Practical (How/Build)**
These test applied knowledge and implementation awareness. Examples:
- "How would you implement X?"
- "Which approach correctly solves Y?"
- "What is the correct order of steps to build Z?"
- "If you observe X during training, what should you do?"

Each question must have exactly 4 answer options labeled A, B, C, and D. Exactly one option is correct. The wrong options should be plausible but clearly incorrect to someone who studied the material.

Tag each question with the specific lesson it draws from (e.g., "Lesson 03: Matrix Transformations").

### Step 4: Present Questions One at a Time

Use the AskUserQuestion tool (or equivalent interactive prompt) to present each question individually. Format:

```text
Question 1/8 (Conceptual) -- from Lesson 03: Matrix Transformations

What is the geometric interpretation of an eigenvalue?

A) The angle of rotation applied by the matrix
B) The factor by which the eigenvector is scaled during transformation
C) The determinant of the transformation matrix
D) The rank of the matrix after transformation
```

Wait for the user's answer before moving to the next question.

### Answer isolation

Keep the correct option and explanation private until the learner answers the
current question. Never use a real answer letter, a likely answer, or the
generated answer distribution in a reply-format hint. When a plain-text hint
is needed, use exactly: `Reply with one letter: <A|B|C|D>.`

### Step 5: Track and Score

Keep a running tally:
- Total correct out of 8
- For each wrong answer, record: the question number, the user's answer, the correct answer, and which lesson it came from

### Step 6: Show Results

After all 8 questions, display the score and grade:

**7-8 correct: Mastered**
If the phase is 19 (Capstone Projects): "You have mastered Phase 19, th

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

[![ModelsAtlas audit: Check Understanding](https://modelsatlas.com/skills/rohitg00/check-understanding/badge.svg)](https://modelsatlas.com/skills/rohitg00/check-understanding/)

Not your listing, or something out of date? Claim or update your listing.