principle-attack-the-premise
Skill0 starsChanged 6 days agoMITView on GitHub
同じ前提に立つ修正が 2 回以上、同じ検査で落ちたとき、または直した部分に次の穴が出たときに適用する。次の修正を書く前に、前提を 1 文に書き出して直接確かめる。
41 other projects use a version of this.
Adopted by
Most recently taken up by
- sammyjoyce/prime-pstacktheir own version, first seen Nov 15, 2026
- upamune/skillstheir own version, first seen Nov 15, 2026
- theishandubey/dotclaudetheir own version, first seen Nov 15, 2026
- mdsmithaustin/pstacktheir own version, first seen Nov 15, 2026
- painhardcore/pstacktheir own version, first seen Nov 8, 2026
- paramcodes/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use principle-explain-the-number, poteto-help and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ianclearySkillprinciple-explain-the-number
Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.
Also in 29 projects that use this
ianclearySkillpoteto-help
Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.
Also in 14 projects that use this
tristanphvnSkillketchup-video
Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.
Also in 10 projects that use this
bnemaSkillsetup-pstack
Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.
Also in 19 projects that use this
eryzerzSkillmake-bot-ui
Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.
Also in 15 projects that use this
TheOnlyFusionCubeSkillmaintain-formal-verification-skill
Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in the verification or a bug in the code. Use for /maintain-formal-verification-skill, \"is the model still true to the code\", or after merges and refactors that touched verified code without rechecking it.
Also in 16 projects that use this
Other versions41 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 41
- backnotprop/pstack★ 3.8ksame name
- jtaroreh/agystack★ 128same name
- uzairansaruzi/p3-stack★ 126same name
- dsebban/skills★ 71same name
- TheOnlyFusionCube/potetos-for-everyone★ 21same name
- creedants/pstack-t3★ 18same name
- painhardcore/pstack★ 18same name
- Scino/fstack★ 18same name
- mariusflorescu/pstack-t3★ 13same name
- adjohn/pstack★ 9same name
31 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository39 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- verify-parallelSkill
- bb-writSkill
- correctSkill
- create-formal-verification-skillSkill
- create-property-test-skillSkill
- create-verification-skillSkill
- delegateSkill
- interrogateSkill
- playbook-bugSkill
- playbook-deliverSkill
- playbook-docs-skillSkill
- playbook-evalSkill
- playbook-featureSkill
- playbook-investigationSkill
- playbook-parallelSkill
- playbook-pause-safelySkill
- playbook-session-pickupSkill
- playbook-verifySkill
- principle-encode-lessons-in-structureSkill
- principle-experience-firstSkill
- principle-fail-loudSkill
- principle-fix-root-causesSkill
- principle-foundational-thinkingSkill
- principle-laziness-protocolSkill
- principle-model-the-domainSkill
- principle-never-block-on-the-humanSkill
- principle-no-budget-cap-on-qualitySkill
- principle-no-speculative-structureSkill
- principle-prove-it-worksSkill
- principle-route-lessonsSkill
- principle-sequence-verifiable-unitsSkill
- principle-single-user-machineSkill
- principle-subtract-before-you-addSkill
- principle-test-behavior-not-implementationSkill
- principle-two-human-rolesSkill
- reflectSkill
- unknownsSkill
The file
Files
前提を疑う
同じ前提に立つ修正が 2 回以上同じ検査で落ちたら、修正でなく前提を疑う。前提を書き出して確かめるまで、次の修正を始めない。
なぜ: 落ちた修正は、それが仮定した考えへの反証になる。同じ前提で 3 つ目の修正を書くと、原因が無いと証拠が示す場所に労力を使う。審査の周では、どの周も「直しが正しいか」を問い、直している仕組みが目的に要るかは誰も問わない。仕組みに直しを足すたびに攻める所が増え、周が止まらない。
適用する場面:
- 2 回続けて同じ受入条件・同じ試験が落ち、また似た修正を足そうとしているとき。
- 「今度こそ」と、閾値・待ち時間・再試行の回数を変えようとしたとき。
- 修正のたびに失敗の形は少し変わるが、落ちる検査は同じとき。
- 審査で、前の直しで足した部分に次の穴が見つかったとき(落ちる検査が周ごとに違っても、前提は「足せば閉じる」で同じ)。
やること:
- 落ちた修正のすべてが仮定していた 1 文を、前提として書き出す。
- 直しが同じ仕組み(足した処理・分岐・試験の土台)に重なっているなら、その仕組みの前提も書き出す。「この仕組みは依頼の目的(測れる値)に要り、仕組みの無い別の形より良い」。目的の値を、仕組みあり・仕組みなし・仕組みの無い別の形(処理を別の単位に分ける、既存の機構に任せるなど)の 3 つで比べる。手元の記録やログから値を出せるなら、それを使う。前提が崩れていれば、仕組みに直しを足さず、別の形に替えるか、仕組みを外す。
- 別の形を否定する文(「〜しても縮まない」「〜では足りない」)は、その形を試すか、手元のデータから値を出してから書く。試さずに書いた否定は、後の審査でも試されず、選択肢を閉じたまま残る。
- 主張が強制の形(「避けられない」「免除できない」「常に」)なら、前提を「結果を変えられる入力の集合は ___ だけである」と書き、データファイル・登録の一覧・設定・fixture・環境・基準の版を 1 つずつ書き換えて確かめる。判定の順序のような局所の前提だけを疑うと、列挙しなかった入力から次の穴が出る。
- 前提が偽なら結果が変わる観察を決めて、行う。失敗の大きさだけでなく、どこに偏って落ちるか(どの対象・どの入力・どの回)を見る。確かめは再実行できるスクリプトにする。
- 証拠が前提に反すれば、前提が予想しなかった失敗の共通点を探す。前提が正しければ、さらに「なぜ」を問う(
principle-fix-root-causes)。どちらでも、条件を後から補う仕組みを足さず、条件を生む原因を取り除く。
使わないとき: 初めて落ちた修正、または落ちた修正がそれぞれ別の前提に立っている場合。新しい要件に合わせて設計を作り直す話でもない。これは、今の設計が仮定している事実を疑う原則。
確かめる例: 2 回目の失敗の後の記録に、前提の 1 文と、それを確かめた観察と結果がある。3 つ目の修正が、同じ前提のまま出ていない。仕組みに直しが重なった後の記録に、目的の値での仕組みあり・なし・別の形の比較がある。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

