Devil's Advocate Pre-Mortem
One honest devil's advocate: steelman your plan, tell how it fails, argue against it, then set tripwires and the cheapest test first.
Before & after
Same prompt, same agent — the only difference is the skill.
Your launch plan sounds solid. Before you go all-in, it's good to think about what could go wrong. You should consider your assumptions—things you believe are true but haven't tested. You should also think about dependencies—what needs to happen first for the rest to work. And of course, there are always execution risks—things that seem simple but turn out to be harder than expected. If you can identify these ahead of time, you'll be better positioned to handle them. Why don't you walk me through the plan, and I can help you think through potential issues?
PRE-MORTEM: PRODUCT LAUNCH PLAN Prompt: "Imagine it's 6 months from now and the launch failed. Work backwards to find what broke." CRITICAL ASSUMPTIONS (Unvalidated) 1. "Sales will close 10 pilots in first month" ⚠ Assumption unchecked: Are 10 target accounts even aware of us? Who drives buying decisions? Risk: Real close rate is 2-3 (70% miss); launch delays 3 months; investor pressure Mitigation: Pre-launch 5 inbound calls with target buyers; validate problem severity (if fake, drop plan) 2. "Product is feature-complete for launch" ⚠ Assumption unchecked: What feature is minimum viable? Who defines done? Risk: Marketing says "30 features ready"; engineering says "5 are shippable"; mismatch = embarrassment Mitigation: Scorecard: 5 core features must hit 95% performance + zero data loss before launch date CRITICAL DEPENDENCIES (Bottlenecks) 1. Data migration (old system → new platform) Risk: If 1 month late, launch slips 1 month (non-negotiable dependency) Mitigation: Migration starts 4 weeks before launch (not day-of); test with 20% of data first 2. Sales team onboarding Risk: If sales only trained 1 week before, they'll fumble messaging; deal close rate drops 40% Mitigation: Sales training starts 4 weeks early; run 3 practice pitches per rep EXECUTION RISKS (Things that sound easy but aren't) 1. Marketing collateral approval cycles (design → legal → CMO → final) Risk: Typical cycle = 3 weeks; if one stakeholder missing, delays 5+ days Mitigation: Get sign-offs in writing 4 weeks before; escalate early 2. Customer support readiness (documentation, ticketing system, first-call scripts) Risk: If support unprepared, 1st customer issue bounces 3x; reputation hit Mitigation: Support runs dry-runs with real scenarios 2 weeks before launch RECOMMENDATION Top 3 actions: (1) Validate problem with 5 buyers NOW; (2) Define 5 core features + freeze scope 4 weeks before; (3) Start migration + sales training 4 weeks out. Compress timelines now so dependencies don't slip. If any buyer validation fails, consider delaying launch 2-4 weeks instead of shipping broken.
About this skill
A single skeptical voice that argues against your plan before reality does. It finds the most plausible ways it fails, not the most dramatic, and turns them into signals you can watch.
What it does
- Steelmans the plan first so the critique targets the real idea
- Names the 1-3 beliefs the plan depends on and whether each is tested
- Writes 3-5 specific, ranked failure stories by type
- Makes the strongest good-faith case for not doing it at all
- Sets early-warning signals, tripwires, and the cheapest test to run first
What you get
A short challenge for a one-line idea, or a full pre-mortem with ranked failure stories, the counter-case, tripwires, the cheapest test, and a one-line verdict. If the plan is strong, it says so.
Best for
Founders, product leads, and teams about to commit budget, people, or a public launch, especially when all feedback so far has been positive.
SKILL.md preview
---
name: devils-advocate-premortem
description: Argue against one plan or idea as a single, honest devil's advocate - steelman it, run a pre-mortem that tells the 3-5 most plausible ways it fails, make the strongest case for not doing it at all, and turn the result into early-warning signals, tripwires, and the cheapest test to run first. Use when the user says "tear this apart", "play devil's advocate", "what am I missing?", "run a pre-mortem on this", "everyone loves this idea, argue against it", "why would this fail?", or "be brutally honest about my plan" before committing money, people, or a public launch.
---
# Devil's Advocate Pre-Mortem
… (sign up to view the full skill)More business & ops skills
View all Business & Ops skills →Simulated Board Pressure Test
Stress-tests a proposal from each board seat's incentives, forecasts the vote, and names the changes that would get it approved.
New Executive Onboarding Plan
First 90 days for a new VP or C-level hire: decision rights from the founder, a measurable scorecard, listening tour, 30/60/90 check-ins.
Change Rollout Planner
Plans how one reorg, tool switch, or pivot lands: impact by group, who hears what first, resistance diagnosis, and follow-through.
CEO Board Prep and Pre-Wires
Gets a CEO ready for the board: likely hard questions by director, number-first answers, pre-wire calls, and a vote count.