| name | notebook-of-things-i-dont-know |
| description | Maintain an explicit ledger of what you don't yet understand. Given a topic, paper, codebase, or conversation, extract the honest gaps — the things named but not grasped — into a tracked list, and turn each into a concrete next step that would close it. Ignorance made visible instead of glossed over. Use when the user says "track what I don't know", "list my knowledge gaps", "what am I missing here", "build my ignorance log", "open questions notebook", "모르는 것 정리해줘", "지식 공백 목록", "이해 안 되는 것 추적". Do NOT use to teach a single concept forward (use feynman-technique) or to hold a standing set of research problems (use twelve-favorite-problems). |
The Notebook Of Things I Don't Know
Feynman kept a literal notebook with that title, then reorganized what he knew
from scratch — because writing down the gaps is what turns vague unease into
a list you can actually close.
Most confusion stays fog: a felt sense that "I don't fully get this" that never
becomes an action. This skill converts fog into a ledger — named gaps, each with
a way to close it — so ignorance is tracked like any other backlog.
Workflow
- Take the source — a topic, paper, codebase area, or the current
conversation.
- Extract honest gaps. Find every place where a term is used but not
understood, a step is accepted on faith, or "I'd have to look that up" is
true. Include the uncomfortable ones — those are the valuable entries.
- Write each as an entry, not a vibe:
gap — the specific thing not understood, phrased precisely.why it matters — what stays blocked while this is open (or "curiosity").next step — the concrete action that would close it (read X, trace Y, run Z).status — open / closing / closed.
- Prioritize. Mark the one or two gaps that block the most, or that
quietly undermine a current decision.
- Persist. Append to a durable file (default
docs/i-dont-know.md, or
wherever the user keeps notes) so the ledger survives the session.
Output
A ledger table — gap | why it matters | next step | status — newest first,
with the highest-leverage open gap called out. On re-runs, update existing
entries (close what's closed) rather than duplicating.
Don't fool yourself
- The temptation is to list only flattering gaps ("minor details"). The entries
that matter are the ones you were about to skip past. Write those.
- A gap with no
next step is a complaint, not an entry. If you can't name a
step, the real gap is "I don't even know how to find out" — write that.
- Closing an entry requires evidence you can now do/explain the thing, not just
that you read about it.
