pre-mortem
/pre-mortem
Wskazuje, jak plan, projekt lub decyzja mogą się nie udać, zanim zostaną zatwierdzone, a także sprawdza plany, które wyglądają zbyt czysto.
- Autor
- pandysp ↗
- Repozytorium
- claude-plugins ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 20.10.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 20.10.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Wskazuje, jak plan, projekt lub decyzja mogą się nie udać, zanim zostaną zatwierdzone, a także sprawdza plany, które wyglądają zbyt czysto.
Wyzwalacze z opisu
Oryginalny opis (EN)
Systematically identify how a plan, design, or decision could fail before committing to it. Trigger when the user invokes the pre-mortem skill, asks "what could go wrong", "failure modes", "risk analysis", or "what am I missing". Also invoke proactively before finalizing significant design decisions, before deploying with irreversible consequences, or when something feels "too clean". Suspiciously few concerns is exactly when pre-mortem matters most.
Jak działa
- Process
- Common pitfalls
Podgląd SKILL.md
--- name: pre-mortem description: Systematically identify how a plan, design, or decision could fail before committing to it. Trigger when the user invokes the pre-mortem skill, asks "what could go wrong", "failure modes", "risk analysis", or "what am I missing". Also invoke proactively before finalizing significant design decisions, before deploying with irreversible consequences, or when something feels "too clean". Suspiciously few concerns is exactly when pre-mortem matters most. --- # Pre-mortem: assume it failed, work backward Imagine this has already failed. What went wrong? The pre-mortem inverts the usual optimistic framing. Instead of asking *"will this work?"* (which biases toward yes), assume it already failed and work backward to figure out why. Surfaces risks that optimism would hide. ## Process ### 1. Set the scene State what's being evaluated, what success looks like, the timeline, and the blast radius. ### 2. Imagine failure Assume it's 3 months later and this failed. Generate failure scenarios across these categories. They're prompts, not a checklist. - **Mechanism**: what breaks under load, scale, or real-world data? Dependency changes? Network slow, disk full, API rate-limits? - **Structure**: where does the design leak? What requirements emerge that this can't accommodate? Where is it optimized for today and fragile against tomorrow? - **Boundary**: what happens at edges with other systems? Upstream contract changes? Data format evolves? - **Human**: what if the next developer misunderstands the design? What if someone uses it in a way you didn't anticipate? Will error messages actually help? - **Operations**: how do you know this is working in production? What's observable? What happens when it fails silently? How do you roll back? After scanning these 5, ask: *what doesn't fit any of these that I should worry about?* Name it as a 6th. The most dangerous failures are often the ones that don't fit the boxes. ### 3. Rank by danger For each failure mode, assess: - **Likelihood**: how probable? (not "could it happen" but "will it happen given enough time") - **Impact**: recoverable annoyance or catastrophic data loss? - **Detectability**: would you know it happened? Silent failures are worse than loud ones. The most dangerous failures are **likely + high-impact + hard to detect**. Lead with those. ### 4. Identify detection strategies For each significant failure mode: *how would you know if it happened?* What metric, log line, user behavior, or test would reveal it? If you can't answer "how would I know?" for a failure mode, that's the most important finding of the whole pre-mortem. ### 5. Present findings Don't soft-pedal. The value of a pre-mortem is uncomfortable honesty before commitment, not reassurance. For each significant failure mode: - **What fails**: specific mechanism, not vague hand-waving. - **Why dangerous**: likelihood × impact × detectability. - **How you'd detect it**: concrete signal. - **What to do**: mitigate now, accept the risk, or redesign. End with a clear recommendation: proceed as-is, proceed with mitigations, or reconsider the approach. ## Common pitfalls - **Listing risks you've already mitigated.** That's not a pre-mortem, that's a victory lap. Focus on what's still exposed. - **"Everything could fail."** Too vague. Name the specific mechanism. - **Only considering technical failures.** Human and operational failures are often more likely. - **Treating it as a formality.** If every pre-mortem ends with "proceed as planned," you're not being honest enough. - **Dramatic register.** State failure modes in neutral, factual language. "Catastrophic" / "disaster" / "irrecoverable" are reserved for actually catastrophic outcomes. Drama sways downstream decisions out of proportion to the actual risk. A recoverable issue framed as apocalyptic gets treated as one.
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · pandysp/claude-plugins | 90 | MIT |
| rjmurillo/ai-agents | 100 | MIT |
| rjmurillo/ai-agents | 100 | MIT |
| borghei/Claude-Skills | 100 | MIT |
| ysskrishna/ai-agent-skills | 100 | MIT |
| fzfclee/consulting-skills | 100 | Apache-2.0 |
| Sidsaladi9/persona-os | 100 | MIT |
| tarunccet/pm-skills | 100 | MIT |
| kaminoikari/product-playbook | 100 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki afbbd5362e3a (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100aped-pre-mortem
Przeprowadza strukturalny pre-mortem przed rozpoczęciem implementacji: co może pójść nie tak, ryzyka i tryby awarii. - 90arn-spark-stress-premortem
Testuje koncepcję produktu metodą pre-mortem Garya Kleina: szuka hipotetycznych przyczyn porażki i sygnałów ostrzegawczych oraz sposobów ograniczenia ryzyka. - 100challenge
Prowadzi pre-mortem: zakłada, że plan się nie udał, i cofa się po przyczynach, żeby wykryć słabe punkty przed realizacją. - 100premortem
Prowadzi analizę pre-mortem decyzji, projektów i inicjatyw, solo lub z zespołem przed startem, w trzech kategoriach ryzyk (krytyczne, postrzegane, przemilczane), a sesje zespołowe kończą się planem działań z właścicielami. - 100swing-mortem
Prowadzi prospektywną analizę porażki metodą pre-mortem Gary'ego Kleina: zakłada całkowitą klapę i cofając się wskazuje ryzyka, wskaźniki wyprzedzające i bezpieczniki dla planów, architektury i premier. - 100inversion-thinking-pre-mortems-failure-modes
Prowadzi pre-mortem projektów technicznych: odwraca plany i z wyprzedzeniem wskazuje katastrofalne tryby awarii.