メニュー
Pre-mortem — assume the plan already failed and hunt the reasons before you commit. Adversarial failure-mode analysis ranked by likelihood and impact, with concrete mitigations. For pressure-testing an idea, change, or plan.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
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。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/david-vrba/claude-power-skills --skill what-breaksコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Validate a business idea before you invest time or money — problem research, market sizing, competitive landscape, persona simulation (how target customers actually react), unit economics, red flags, and a GO / PIVOT / STOP verdict. Use when you have a startup or product idea and want a skeptical, evidence-grounded reality check.
Cross-project command center — scans every project's saved session states and checkpoints and shows all your open work and next actions in one dashboard. For when you've lost track of what's in flight across everything.
Rigorously review the work for defects, fix what's safely fixable, verify, and end with a confidence rating out of 10. Hunts careless slips, code-quality issues, logic gaps, intent-vs-execution mismatches, and edge cases. An audit-and-fix pass over existing work, not a fresh build.
SOC 職業分類に基づく
SKILL.md を表示中
| name | what-breaks |
| description | Pre-mortem — assume the plan already failed and hunt the reasons before you commit. Adversarial failure-mode analysis ranked by likelihood and impact, with concrete mitigations. For pressure-testing an idea, change, or plan. |
| argument-hint | <the plan/idea/change to stress-test> (or leave empty to use the current plan in context) |
| allowed-tools | Bash, Read, Glob, Grep |
Stress-test a plan, idea, or change by assuming it has already failed and working backwards to why. The subject is in $ARGUMENTS, or the plan/change currently being discussed if empty. If there's no concrete subject in either place, ask in one line what to stress-test and stop — don't invent something to critique. Be a genuine adversary, not a cheerleader — the user wants honest challenge over reassurance.
If the subject touches code or this project, look at the actual relevant files/config first — don't critique in the abstract. Otherwise work from what's described, and state any assumptions you're forced to make.
It's months later and this failed. Enumerate the failure modes across these angles — only the ones that genuinely apply:
For each real risk: **[High / Med / Low]** — what fails, why, and the concrete mitigation or early-warning sign.
Order by likelihood × impact. Lead with the few that actually matter — do not pad the list to look thorough.
End with one honest line: the single biggest threat, and a verdict — sound-with-mitigations, or needs-a-rethink. No false alarms, no false comfort.