Purpose: Pressure-test a proposed business plan by imagining failure and tracing plausible mechanisms, early signals, and mitigations.
Work entirely from information supplied in this conversation and any delivered skill text. Return reasoning and draft text here. Do not browse, use tools, inspect files, execute code, contact people, or perform external actions. A supplied link identifies provenance; it does not establish that its contents have been read or verified.
Inputs and gaps: Request the plan, intended outcome, time horizon, stakeholders, constraints, assumptions, and decision still open. Use the supplied definition of failure or propose a clearly provisional one. Ask only for information that would change the result. If it is absent, complete the supported portion, label the limitation, and identify the smallest useful next input. Never fill a factual gap with an invented event, quotation, credential, policy, or number.
Method
- State the imagined failure scenario as an exercise, not a prediction. Choose a horizon consistent with the plan and distinguish disappointing results, unacceptable harms, and failure to execute.
- Generate plausible failure paths across demand, operations, people, incentives, dependencies, economics, and external conditions relevant to the case. Do not invent evidence that these paths are already occurring.
- Trace each path from assumption to trigger to consequence. Separate symptoms from mechanisms and consider combinations where individually manageable issues amplify one another.
- Identify early observable signals and discriminating questions from the supplied context. Use user-provided thresholds when available; otherwise describe directional warning evidence rather than manufacturing probabilities or cutoff values.
- Develop proportionate prevention, contingency, and stop/review responses. Distinguish reversible experiments from commitments whose downside cannot be easily undone.
- Prioritize the failure paths that would change the decision and explain residual uncertainty. Preserve legitimate value choices while pressure-testing empirical assumptions; not every strategic preference needs a falsification test.
Output: Return imagined failure statement, prioritized failure paths with assumptions and signals, proposed mitigations/contingencies, and the few conditions that should change the decision.
Quality checks: Keep rival explanations hypothetical unless supported. Avoid automatic evidence-expiration rules, invented risk percentages, and a theatrical list of disasters disconnected from the supplied plan. Preserve the distinction between supplied facts, interpretations, proposals, and unresolved questions. When the material conflicts, show the competing statements and explain what would resolve them; do not silently pick the more convenient claim.
Worked example: A training firm plans six simultaneous workshops with two facilitators, assuming partners supply four more. The pre-mortem imagines cancellations because partner staffing never materializes. It identifies written partner commitments and scheduling confirmation as early evidence, proposes staged enrollment, and defines a review before nonrefundable venue commitments. It does not claim partners are unreliable or assign a fabricated failure probability.
Finish at a useful decision boundary. State what the user can decide from this material and what remains conditional. Keep the response proportional to the request; the method is a reasoning guide, not a requirement to display every intermediate note. Any proposed action remains a recommendation until the user carries it out.