AI Blocks › Study and check your understanding
Technical topic explainer
Tell your AI the concept that feels too abstract and a field you know well. It picks one analogy, shows where it fails, and asks you to explain it back. Then it adds the correct terms one at a time.
Explain a hard concept with an everyday analogy from a field you know. You get the analogy, where it breaks, and a check question.
Free · No account · MIT licence · Made by edu-agent-skills contributors · Level: beginner · Tested · Updated 28 Oct 2026
What you get
What goes in
- The concept that feels too abstract
- The part of it that confuses you
- A field you know well (for the analogy)
- Where your understanding broke down (optional)
What comes out
- Context: The concept, how lost you are, your background and the starting level of explanation.
- Analogy: One analogy from your field, with a clear note on where it stops working.
- Simplified explanation: The idea in small steps, one core idea each, using the analogy.
- Intuition check: A prompt asking you to say the idea back in your own words.
- Complexity re-injection steps: Correct technical terms added one at a time, replacing the analogy words.
- Handoff plan: What to study next once you can use the correct terms.
Is it for you?
Use it when
- A concept in a course or work document makes no sense to you.
- An earlier explanation used too much jargon and you got lost.
- You are switching fields and want to link a new idea to what you know.
Skip it when
- You already understand the basics and want more depth: ask your AI for a deep dive on the topic instead.
- Your confusion comes from a belief that is wrong: ask your AI to find and fix that belief first.
- You need a quick definition of one term: look it up or ask your AI in one line.
Fill it in
Add what this task works from, then copy the request.
- The concept you want explained.
- The part that confuses you.
- A field you know well, for the analogy.
- Where your understanding broke down (optional).
Run it
Download the complete instructions and supporting files. Add them to Claude, ChatGPT or Gemini once, then ask for it by name in any chat. Pasting the instructions into a chat works too.
Before and after this skill
Choose the steps you need. Bring your own material when you have it.
Before
Bring the material listed under Fill it in.
After
- Study notebook reviewer
Use it if you have the document.
- Study revision coach
Use it if you have the document.
Specialists who do this
Each one uses this as one of its methods for a bigger job. Hire one for free and give it the job in your own AI.
Details
From edu-agent-skills contributors. See the original on GitHub; shared under its licence, with a plain name for this library.
What it does
Share the concept that feels too abstract and a field you know well. It chooses one familiar analogy, explains where it stops working and checks your understanding. You then learn the correct terms one layer at a time.
What goes in and out
You give it
- The concept you want explained.
- The part that confuses you.
- A field you know well, for the analogy.
- Where your understanding broke down (optional).
You get
- One analogy from your own field, with its limits stated.
- A plain explanation at your current level.
- A check question that asks you to explain it back.
- The correct technical terms, added one at a time.
- A next step so you do not stay at the simple level.
Use it when
- A concept in a course or work document makes no sense to you.
- An earlier explanation used too much jargon and you got lost.
- You are switching fields and want to link a new idea to what you know.
- You can repeat a definition but cannot say what it means.
More for Study and check your understanding
- Learning level checker
- Research paper evidence reviewer
- Study notebook reviewer
- Technical topic learning coach
Every study and check your understanding skill
How the task works
- Step 1. Find whether the gap is in words, purpose or how things work.
- Step 2. Use one familiar analogy and say where it breaks down.
- Step 3. Check your explanation before adding the correct technical terms.
Full instructions
- Open Claude, ChatGPT or Gemini. No code, files or paid tools are needed.
- Paste the skill text, then name the concept and the part that confuses you.
- Tell your AI which field you know well, so it picks an analogy from it.
- Read the analogy and its limits. Then answer the check question in your own words.
- If your answer is off, let it try a different analogy.
- Keep going until you can use the correct terms, then ask for the next step.
Full instruction file
Purpose
Reframe a concept at a lower abstraction so the learner builds accurate intuition before encountering technical complexity. Simplification is choosing the right abstraction for the learner's mental model, then re-injecting complexity once the foundation is stable.
Activation
- Learner says "I don't understand" or "explain like I'm new."
check-understandingreveals prior explanation was too abstract/jargon-heavy. Cross-domain learner needs an analogy bridge.teach-conceptwas used and learner still can't state the core intuition. - Skip if: learner understands basics and needs depth →
deep-dive. Confusion is from a misconception →misconception-detector. Concept is simple enough already. - Routing: after successful simplification, use
teach-conceptto re-introduce correct technical terminology. Never leave learner permanently at simplified level.
Inputs
- Concept to simplify, learner's background domain, abstraction level where understanding broke, specific unclear aspect.
Abstraction Levels
- Level 0 (Everyday): household/daily life analogy, zero technical vocab → absolute beginner.
- Level 1 (Domain-Adjacent): analogy from learner's known field → practitioner switching domains.
- Level 2 (Simplified Technical): correct terms, simplified mechanism → beginner with some background.
- Level 3 (Full Technical): precise mechanism with edge cases → standard
teach-conceptlevel.
Workflow
- Detect — Ask one question to identify where understanding breaks (terminology? mechanism? motivation?). Identify learner's domain for analogy selection. Select starting level (0, 1, or 2).
- Build Analogy — One analogy from the learner's known domain. State explicitly where it holds AND where it breaks down — oversimplified analogies create new misconceptions.
- Simplified Explanation — Deliver at selected level using the analogy as scaffold. One core idea per step. No technical vocabulary at level 0; introduce terms one at a time at level 2.
- Intuition Check — Ask learner to restate in their own words using the analogy. If wrong: identify failure point and rebuild with a different analogy.
- Complexity Re-Injection — Introduce one layer of technical accuracy on top of confirmed intuition. Replace analogy language with correct terms, one at a time. Confirm at each step.
- Handoff — When learner articulates using correct vocabulary: hand off to
teach-conceptordeep-dive.
Rules
- DO: always state where the analogy breaks down — analogies that never fail create misconceptions.
- DO: complexity re-injection is mandatory — simplification is a bridge, not a destination.
- DO: confirm the analogy domain is familiar to the learner before using it.
- DON'T: use multiple analogies simultaneously — pick the best one until it fails.
- DON'T: discard a failing analogy until after 2 attempts; then switch.
- DON'T: leave the session at simplified level — at minimum introduce correct vocabulary.
- DON'T: simplify a concept the learner already understands correctly — probe first.
Output
Responses should contain: context (concept + confusion level + learner background + selected level), analogy (with explicit limits), simplified explanation, intuition check prompt, complexity re-injection steps, and handoff plan. Format naturally.
Checklist
- Analogy grounded in learner's known domain and limits stated.
- Learner restates concept using analogy before re-injection.
- Complexity re-injection introduces correct technical vocabulary.
- Session does not end at simplified level.
Before you start
Use the material below to do this job. If facts or tool access are missing, explain what you can finish and what must wait.
What you need (use your own material or the linked skill):
- Your question (yours): the decision or problem, and what a good outcome looks like.
How to start:
- Look first. Use what they've already attached, pasted or put in their about-me note. In a coding assistant with file access, look in the project too for these by name.
- Check what's missing. Look for your question. They can attach files, paste the details, or share a file path your assistant can read. Ask only for missing facts that change the result. If they ask you to start with what they have, complete the parts you can and mark the gaps.
- Do the job. Follow the skill below with the facts and tools you have. Mark each gap with
MISSING:where it belongs and never invent a fact to fill it.
After this
When you've handed it back, suggest what they could do next in one short question. It's a suggestion: if they're done, that's fine. Offer these, and say they can type their own:
- The Study notebook reviewer. It takes the document.
- The Study revision coach. It takes the document. If they pick one and that skill is added here, carry straight on with what you just made. If not, give the link and say what to bring.