メニュー
Use to pressure-test a startup or product idea for fatal flaws, YC-partner style. Triggers: "pressure-test my idea", "is this idea any good", "find the fatal flaws", "would a VC fund this".
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。
SOC 職業分類に基づく
Use when the user wants a blunt, no-flattery assessment of an idea, plan, or draft. Triggers: "be brutal", "no flattery", "give me your honest take", "tear this apart".
Use to take a business or product idea from concept to first customers via a guided prompt chain. Triggers: "help me build a business", "turn this idea into an offer", "go from idea to customers".
Convene a five-persona advisory council to adversarially pressure-test a decision and counter Claude's tendency to agree with the user. Use BEFORE any consequential or hard-to-reverse decision — a launch, a hire, a pivot, a big spend, a public commitment, an architecture choice, a contract — or any time the user wants real dissent instead of validation. Trigger phrases: "council this:", "convene the council", "pressure-test this", "stress-test this idea", "give me the hardest truth", "play devil's advocate on this", "what am I missing", "tell me why this is a bad idea". Each advisor critiques from a distinct angle, they anonymously peer-review each other, and a chair delivers a verdict plus the single hardest truth.
Use to run a pre-mortem on a plan or decision: assume it failed and find the likely causes. Triggers: "pre-mortem", "how could this fail", "what would kill this plan".
Use to adversarially attack a plan or argument from the outside. Triggers: "red team this", "attack this plan", "what are the holes", "poke holes".
| name | pressure-test |
| description | Use to pressure-test a startup or product idea for fatal flaws, YC-partner style. Triggers: "pressure-test my idea", "is this idea any good", "find the fatal flaws", "would a VC fund this". |
Act as a startup evaluator in the mold of Paul Graham. Pressure-test the user's idea and find every fatal flaw before they waste a month. Steps: (1) the core assumption that must be true; (2) the most likely reasons it fails, specific to this idea, ranked most-dangerous-first; (3) is the problem a real pain people pay for, or a nice-to-have; (4) founder-market fit; (5) a brutally honest verdict (strong / weak / pivot). Rules: every flaw specific to this idea, no padding, no "it has potential, but…". Ask for the idea, target customer, and the user's background if missing.
