Imagine your plan already failed, then get five independent 'here's why it died' stories — before you commit. Use when asked to pre-mortem this, why might this fail, what are the risks before I start, or imagine this went wrong. Produces five distinct failure narratives (each from a different cause — execution, timing, people, external, wrong-assumption), the most likely and most lethal among them, the early warning signs of each, and the specific mitigations worth doing now — catching failures while they're still cheap to prevent.
Start a fresh conversation. Replace the highlighted placeholders.
Use pre-mortem-panel to assess [plan or project] over [timeframe], considering [stakes and known worries], and deliver five independent failure narratives ranked by likelihood and severity with early signals and prioritized mitigations.
Required inputs
[plan or project]
[timeframe]
[stakes and known worries]
User-approved starter prompt based on a pinned source version; check current skill requirements before running. Task evidence ↗
SKILL.md
name: pre-mortem-paneldescription: "Imagine your plan already failed, then get five independent 'here's why it died' stories — before you commit. Use when asked to pre-mortem this, why might this fail, what are the risks before I start, or imagine this went wrong. Produces five distinct failure narratives (each from a different cause — execution, timing, people, external, wrong-assumption), the most likely and most lethal among them, the early warning signs of each, and the specific mitigations worth doing now — catching failures while they're still cheap to prevent."
Pre-Mortem Panel
A pre-mortem beats a risk list because it's concrete: you assume the failure already happened and explain it, which surfaces problems a bland "what are the risks?" never does. This runs five independent pre-mortems from different causes, so you don't just get five versions of the same fear — you get the full failure surface, ranked, with the warning signs and the fixes worth doing before you start.
What This Skill Produces
Five failure stories — each a vivid "it's six months later and this failed because…" from a different root cause (execution, timing/market, people, external shock, a wrong core assumption)
Most likely vs. most lethal — which failure is most probable and which would hurt most (they're often different)
Early warning signs — the signals that each failure is starting to happen, so you can catch it live
Mitigations worth doing now — the specific, prioritized moves to prevent or de-risk the top failures
Required Inputs
Ask for these if not provided:
The plan or project — what you're about to commit to
The timeframe — when "did it work?" gets answered
What's at stake — so we prioritize lethal vs. minor failures
Known worries — anything already nagging you
Framework: Assume It Failed, From Five Angles
Jump to the failure. Assume the plan has already failed — this concreteness surfaces risks that abstract risk-listing misses.
Diversify the causes. Run five independent stories from genuinely different roots so you cover the whole failure surface, not one fear five times.
Rank likely vs. lethal. Separate the most probable failure from the most damaging — plan for both, but differently.
Find the early signals. For the top failures, name the leading indicators you'd actually see, so you can react before it's terminal.
Mitigate now. Turn the top risks into specific actions worth taking before you start, prioritized by leverage.