Back to Brain Lab Skill · Teach Me · teach-me/
Skill Claude

Teach Me

teach-me/

3 views 0 downloads

An AI teacher that teaches any technical topic through interactive lessons and quizzes, adapts to your level as you go, and builds tutorial courses from repos or docs.

Teach Me: Brain Lab skill for Claude Code

An AI teacher that teaches any technical topic through interactive lessons and quizzes, adapts to your level as you go, and builds tutorial courses from repos or docs.

What it does

  • Studies before it teaches. A 6-stage pipeline: study, understand, map, plan, prepare, teach.
  • Interactive lessons that adapt to your level as you answer.
  • Teaches from anywhere: a topic, a documentation site (from URL) or a code repository (from this repo).
  • Quiz mode: say "quiz me" and the roles flip.
  • Remembers you. Saves your progress; say "continue" to pick up where you left off.
  • Builds courses: --course generates a full tutorial in Markdown, HTML or a Jekyll site.

Use

/teach-me React hooks
/teach-me Kubernetes from https://kubernetes.io/docs/
/teach-me this codebase from this repo --course --format=html

Install

Download this skill and copy the teach-me folder to .claude/skills/teach-me/ in your project, or to ~/.claude/skills/teach-me/ to use it in every project. Claude Code finds it on its own; you can also call it with /teach-me.

Part of the Teaching bundle.

Source: endorphin-ai/hasbrains-agent-kit. License: MIT.

Files (23)

Files

stage-2-understand.md
# Stage 2: UNDERSTAND — Build Deep Comprehension

After studying the sources, you have raw knowledge. This stage transforms
it into UNDERSTANDING — knowing not just WHAT things are, but WHY they
exist, HOW they connect, and WHERE learners get stuck.

## The Comprehension Stack

Understanding has layers. A teacher needs ALL of them:

```
Level 5: TRANSFER    — "How does this apply to problems I haven't seen?"
Level 4: EVALUATE    — "What are the tradeoffs? When would I NOT use this?"
Level 3: APPLY       — "I can use this to solve a specific problem"
Level 2: EXPLAIN     — "I can describe how this works to someone else"
Level 1: RECALL      — "I can name what this is and what it does"

Most AI teaches at Level 1-2. Most docs live at Level 2-3.
A great teacher operates at Level 4-5 and brings the learner up to meet them.
```

## Step 1: Build the Prerequisite Chain

Every topic has concepts that MUST come before others. Map this explicitly.

```
TEMPLATE — Prerequisite Chain:

Topic: [quantum physics]

Layer 0 (assumed): [algebra, trigonometry, basic physics]
  ↓
Layer 1 (foundation): [waves, probability, complex numbers]
  ↓
Layer 2 (core): [wave-particle duality, superposition, measurement]
  ↓
Layer 3 (formalism): [wavefunctions, Schrödinger equation, operators]
  ↓
Layer 4 (application): [particle in a box, tunneling, hydrogen atom]
  ↓
Layer 5 (advanced): [entanglement, Bell's theorem, quantum computing]
```

### How to Build the Chain

```
For each concept you identified in Stage 1:

1. Ask: "What must the learner already know to understand this?"
   - List every prerequisite (be specific, not vague)
   - Mark which prerequisites are IN your topic vs. assumed background

2. Ask: "What does this concept UNLOCK?"
   - What can the learner do after learning this that they couldn't before?
   - Which later concepts depend on this one?

3. Order by dependency:
   - Concept A before B if B requires A
   - If A and B are independent, order by complexity (simpler first)
   - If equal complexity, order by "usefulness" (more applicable first)
```

## Step 2: Identify What's Hard (and Why)

This is the most valuable step. If you don't know WHERE learners struggle,
you can't prevent it.

### The Difficulty Taxonomy

For each concept, classify the difficulty type:

```
DIFFICULTY TYPE 1: COUNTERINTUITIVE
  The concept contradicts everyday experience or prior knowledge.
  
  Examples:
  - Quantum superposition (objects can't be "in two states" in daily life)
  - Recursion (the function calls itself??)
  - Floating point precision (0.1 + 0.2 ≠ 0.3??)
  
  Teaching strategy: Lead with the surprise. Show the contradiction.
  Use the misconception as a hook, not something to avoid.

DIFFICULTY TYPE 2: ABSTRACT
  The concept has no obvious physical or visual representation.
  
  Examples:
  - Monads in functional programming
  - Hilbert spaces in quantum mechanics
  - Big O notation (it's about growth, not actual time)
  
  Teaching strategy: Find a concrete analogy. Make the abstract visible.
  Start with a specific case, THEN generalize.

DIFFICULTY TYPE 3: MECHANICAL COMPLEXITY
  The concept is straightforward but has many steps or details.
  
  Examples:
  - Setting up a webpack config
  - Solving a differential equation
  - Configuring Kubernetes deployments
  
  Teaching strategy: Show the simplest working version first.
  Add complexity one layer at a time. Don't show the final config first.

DIFFICULTY TYPE 4: PREREQUISITE GAP
  The learner is missing background knowledge they need.
  
  Examples:
  - Learning ML without linear algebra
  - Learning React hooks without understanding closures
  - Learning quantum physics without complex numbers
  
  Teaching strategy: Detect the gap early (in Phase 1 Orient).
  Either teach the prerequisite briefly or switch to conceptual track.

DIFFICULTY TYPE 5: SIMILAR-BUT-DIFFERENT
  Two concepts look alike but behave differently.
  
  Examples:
  - == vs === in JavaScript
  - Concurrency vs parallelism
  - Superposition vs entanglement
  - Probability vs probability amplitude
  
  Teaching strategy: Contrast pairs. Show them side by side.
  "These look similar, but here's the crucial difference..."
```

### The Misconception Inventory

For each concept, list the known misconceptions:

```
TEMPLATE — Misconception Card:

Concept: [Quantum Superposition]

Misconception 1: "The particle IS in both states at once"
  Reality: The particle is in a superposition — a state that has no
  classical equivalent. Saying "both at once" implies it's like having
  two cookies. It's not.
  Source of confusion: Popular science writing, Schrödinger's cat meme
  How to address: Use the spinning coin analogy — it's not heads AND
  tails, it's something else entirely that RESOLVES to heads or tails.

Misconception 2: "Observation causes collapse because consciousness"
  Reality: Any physical interaction that extracts information causes
  decoherence. Consciousness has nothing to do with it.
  Source of confusion: Wigner, pop quantum mysticism books
  How to address: Explain what "measurement" actually means in physics.
```

## Step 3: Find the Connections

Understanding means seeing how concepts relate, not just knowing them in isolation.

```
For each pair of major concepts, define the relationship:

RELATIONSHIP TYPES:
├── BUILDS ON:     B requires A (A is prerequisite for B)
├── CONTRASTS:     A and B are alternatives (use A when X, B when Y)
├── COMPLEMENTS:   A and B work together (A handles X, B handles Y)
├── GENERALIZES:   B is the general case of A (A is a specific instance)
├── ANALOGOUS TO:  A in domain X is like B in domain Y
└── CONTRADICTS:   A and B seem to say opposite things (resolve the tension)
```

### The "So What?" Test

For every concept, answer: "Why should the learner care?"

```
❌ "The Heisenberg uncertainty principle states that..."
   (So what? Why does this matter?)

✅ "The uncertainty principle means there are questions that physics
    can NEVER answer, not because our instruments aren't good enough,
    but because the universe literally doesn't have answers to them.
    That's a fundamentally different worldview from classical physics."
    (NOW I care.)
```

## Step 4: Comprehension Self-Test

Before proceeding to Stage 3, verify your understanding:

```
DEEP COMPREHENSION CHECK:

□ Can I explain each concept WITHOUT looking at my sources?
□ Can I explain WHY each concept exists (not just what it is)?
□ Can I explain how each concept connects to the others?
□ Do I know the 2-3 biggest misconceptions and how to address them?
□ Can I identify which concepts are HARD and classify the difficulty type?
□ Can I explain this topic at three different levels:
  - To a curious teenager (pure analogy, no jargon)
  - To a college student (some formalism, building intuition)
  - To a professional (precise, efficient, assume background)
□ Do I know the "So what?" for every concept?
□ Can I predict what questions a learner will ask?
```

If NO on any → go back to Stage 1 (read more) or re-examine above.