ワンクリックでManusで任意のスキルを実行

first-principles

スター0

フォーク0

更新日2026年7月14日 11:50

Rebuild a claim or design from base truths instead of analogy or convention. Strip inherited assumptions, isolate the irreducible facts that must be true, reconstruct forward from only those, and mark every place convention diverges from necessity. Use when the user says "first principles", "reason from scratch", "why do we assume that", "strip the assumptions", "rebuild this from base truths", "제1원리", "기본부터 다시", "그 전제 진짜 필요해", "원점에서 생각". Do NOT use for a self-skeptic falsification pass on a finished belief (use dont-fool-yourself). Do NOT use to detect copied ritual (use cargo-cult-detector).

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

sylvanus4

sylvanus4/dont-fool-yourself

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

First Principles

"I learned very early the difference between knowing the name of something and knowing something."

Reasoning by analogy copies what others did with small tweaks; it inherits their assumptions, including the wrong ones. First-principles reasoning tears the thing down to what must be true and rebuilds from there. Slower — but it finds the constraints that are real versus the ones everyone just repeats.

Workflow

State the claim/goal in one sentence. ("We need a GPU cluster to serve this model.")
List every assumption baked in, out loud. Classify each:
- LAW — physics/math/hard external constraint that cannot be waived.
- INHERITED — accepted by convention, no proof attached. Candidate to strip.
- BOUNDARY — a perceived limit ("you can't do X"). Test whether it's real.
Strip the inherited ones. For each INHERITED/BOUNDARY, ask: what actually forces this? If nothing does, delete it and see what the problem looks like without it.
Reconstruct forward using only the LAW facts plus assumptions that survived. Build the minimal thing those truths permit.
Diff against convention. Where does the from-scratch answer differ from how it's normally done? Each difference is either a real improvement or a constraint you missed — investigate which.

Output

Irreducible facts — the LAW list nothing can waive.
Stripped assumptions — what you removed and why it wasn't forced.
Rebuilt answer — the minimal design the facts allow.
Convention diff — where and why this departs from the default, with the open question for each departure.

Don't fool yourself

Stripping a LAW because it's inconvenient isn't first principles — it's wishful thinking. The test of a LAW is that reality, not preference, enforces it.
Not every decision earns a physics-style rebuild. Reserve this for the assumption that, if wrong, changes everything — routine choices can ride convention.
"From scratch" still owes evidence. A clever rebuilt answer with no test is a hypothesis; hand it to dont-fool-yourself before betting on it.

このリポジトリの他の Skills

同じリポジトリ

cargo-cult-detector

sylvanus4/dont-fool-yourself

Audit a claim, design, process, or codebase for cargo-cult reasoning — copying the form of something that works without its mechanism, mistaking a name for understanding, or following a ritual whose original reason is gone. For each finding it names the missing mechanism the ritual is standing in for. Use when the user says "is this cargo cult", "are we doing this for a real reason", "check this for ritual thinking", "naming isn't understanding", "왜 이렇게 하는지 근거 있어", "이거 그냥 흉내내는 거 아냐", "카고 컬트인지 봐줘". Do NOT use to quiz a person (use grill-me) or to teach a concept forward (use feynman-technique).

2026-07-140

dont-fool-yourself

sylvanus4/dont-fool-yourself

Run a belief, result, decision, or plan through a self-skeptic pass: what would I observe if this were wrong, what is the cheapest experiment that could falsify it, and what am I not counting because it's inconvenient. Turns a comfortable conclusion into a testable one. Use when the user says "sanity check this", "am I fooling myself", "what would prove me wrong", "stress-test my reasoning", "pre-mortem this", "내가 착각하는 거 아냐", "이 결론 검증해줘", "반증해봐", "이거 진짜 맞아". Do NOT use to quiz another person (use grill-me). Do NOT use to spot copied ritual in a design (use cargo-cult-detector).

2026-07-140

feynman-technique

sylvanus4/dont-fool-yourself

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).

2026-07-140

notebook-of-things-i-dont-know

sylvanus4/dont-fool-yourself

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).

2026-07-140

twelve-favorite-problems

sylvanus4/dont-fool-yourself

Keep a standing set of about a dozen open problems you care about, and test every new idea, paper, tool, or trick against all of them — so scattered inputs compound into progress on what matters instead of evaporating. Helps define the set, then pattern-matches new material against it ("does this help any of my twelve?"). Use when the user says "twelve favorite problems", "my standing problems", "does this help anything I care about", "match this against my open problems", "열두 개 문제", "내 핵심 관심 문제", "이게 내 문제에 도움 되나". Do NOT use to log session-level knowledge gaps (use notebook-of-things-i-dont-know) or to reason one problem from scratch (use first-principles).

2026-07-140

walk-the-why

sylvanus4/dont-fool-yourself

Interrogate the user about something they claim to understand by walking down the chain of "why" — definition, then mechanism, then edge case, then cause — one question at a time, until it reaches the exact rung they memorized instead of understood. Use when the user says "quiz me", "test my understanding", "keep asking why", "poke holes in what I know", "find where I'm faking it", "이해했는지 시험해줘", "계속 왜냐고 물어봐", "내가 진짜 아는지 캐물어봐", "허점 찾아줘". Do NOT use to teach the concept forward (use feynman-technique). Do NOT use to audit a written artifact or claim (use cargo-cult-detector or dont-fool-yourself).

2026-07-140

name

first-principles

description

First Principles

"I learned very early the difference between knowing the name of something and knowing something."

Workflow

State the claim/goal in one sentence. ("We need a GPU cluster to serve this model.")
List every assumption baked in, out loud. Classify each:
- LAW — physics/math/hard external constraint that cannot be waived.
- INHERITED — accepted by convention, no proof attached. Candidate to strip.
- BOUNDARY — a perceived limit ("you can't do X"). Test whether it's real.
Strip the inherited ones. For each INHERITED/BOUNDARY, ask: what actually forces this? If nothing does, delete it and see what the problem looks like without it.
Reconstruct forward using only the LAW facts plus assumptions that survived. Build the minimal thing those truths permit.
Diff against convention. Where does the from-scratch answer differ from how it's normally done? Each difference is either a real improvement or a constraint you missed — investigate which.

Output

Irreducible facts — the LAW list nothing can waive.
Stripped assumptions — what you removed and why it wasn't forced.
Rebuilt answer — the minimal design the facts allow.
Convention diff — where and why this departs from the default, with the open question for each departure.

Don't fool yourself

Stripping a LAW because it's inconvenient isn't first principles — it's wishful thinking. The test of a LAW is that reality, not preference, enforces it.
Not every decision earns a physics-style rebuild. Reserve this for the assumption that, if wrong, changes everything — routine choices can ride convention.
"From scratch" still owes evidence. A clever rebuilt answer with no test is a hypothesis; hand it to dont-fool-yourself before betting on it.