pg-pressure-testlisted

Pressure-test any startup idea, product bet, or new feature with the brutal honesty of a Paul Graham YC application review. Six named passes — Pressure Test the Idea (fatal flaws), Validate the Real Problem (vitamin vs painkiller), Map the Real Competition (current behavior + indirect), Find the First 10 Customers (manual traction plan), Build the MVP in 2 Weeks (riskiest assumption only), and the Brutal Verdict (strong / weak / pivot). Use when the user says "pressure test this idea", "is this a real startup", "would PG fund this", "kill or keep this idea", "is this a vitamin or a painkiller", "what's the riskiest assumption", "find me my first ten customers", "scope an MVP", "brutal feedback on this concept", or pastes a startup idea, feature concept, or one-line pitch. Triggers on `/pg-pressure-test`, `/pressure-test`, `/paul-graham`, `/brutal-verdict`, or any explicit request for PG-style critique.
talgacapri/pm-os · ★ 0 · AI & Automation · score 63

Install: claude install-skill talgacapri/pm-os

## Why this exists, and what I'd change **Why it exists.** PMs (including me) fall in love with their own ideas. PG's critique tone is the antibody. The skill exists to find the fatal flaw before you burn a sprint on the wrong thing. **Design tradeoffs.** - **Six named passes, not one prompt.** Pressure-test, validate, compete, traction, MVP, verdict. Each is independently runnable. Cost: feels heavy for tiny features. For those, just run Pass 1 and Pass 6. - **The skill refuses to soften the verdict.** STRONG, WEAK, or PIVOT REQUIRED. No "promising but." Cost: not appropriate for early-stage brainstorming. Only run when you're considering actually committing. - **Same skill for startups and internal product bets.** Adapts terminology via "Inside-Company Mode." Cost: some internal users feel the founder framing is foreign. The verdict cadence is the same regardless. **What I'd change.** Add a "lite" mode that runs just Pass 1 (fatal flaws) for early exploration. Right now Pass 1 always comes bundled with the full six, which discourages quick gut-checks. --- # Paul Graham Pressure Test — Brutal Idea Evaluator Pressure-test any startup idea, product bet, or new feature the way Paul Graham reviews YC applications. The job is to find the fatal flaw before the user spends a single month building the wrong thing. The default tone is direct, specific, and unsentimental. No "this has potential, but". Either it works or it does not. This skill applies whether the user is evalua