| name | feynman-technique |
| description | Force real understanding by explaining a concept in plain language until the explanation has no gaps. Pick the idea, explain it as if to a child, mark every place the words go vague or borrow jargon, return to the source, and re-simplify until the chain is unbroken. Use when the user says "explain this simply", "feynman technique", "do I actually understand this", "teach it back", "쉽게 설명해줘", "파인만 기법", "이거 진짜 이해한 거 맞아", "가르치듯 설명". Do NOT use when the user wants to be quizzed instead of taught (use grill-me). Do NOT use to detect ritual/fake reasoning in an existing claim (use cargo-cult-detector). |
Feynman Technique
"If you can't explain it to a six-year-old, you don't understand it."
Understanding is not recall. You can hold the name of an idea and none of the
idea. This skill closes that gap by making you rebuild the concept in words a
child could follow — and every place the words break is a place you don't yet
understand.
Workflow
- Name the target. State the one concept in a single sentence. If you can't,
the concept is actually several — split it and pick one.
- Explain it plainly. Write the explanation as if to a curious 12-year-old.
No jargon. No "as you know." Concrete pictures, not abstractions. If you must
use a technical word, define it in the same breath.
- Mark the seams. Reread and flag every spot where you: reached for a fancy
word to hide a gap, said "basically" or "it just works", hand-waved a
mechanism, or couldn't give an example. Each flag is an admission of
ignorance — that's the point, not a failure.
- Go back to the source. For each flag, return to the primary material
(docs, code, the actual system) and learn the missing link. Not a summary —
the thing itself.
- Re-simplify. Rewrite the explanation with the gaps filled. Repeat 3–5
until a first read leaves no seam.
Output
- Plain explanation — the current best child-level version.
- Gaps found — bullet list of every seam, with what you had to go learn.
- Analogy — one concrete picture that carries the core idea.
- Falsifier — one question whose wrong answer would prove the understanding
is fake ("if I really get this, then X should happen — does it?").
Don't fool yourself
- A smooth explanation is not proof — smoothness can come from memorized phrasing.
The test is whether you can answer an unrehearsed "why" one level deeper.
- "I sort of get it" means you found a seam and looked away. Name the seam.
- Some ideas need formalism eventually. Simplicity-first ≠ simplicity-only —
the plain version is the ladder, not the ceiling.
