premortem-to-fmea-pipeline
$
npx mdskill add yogsoth-ai/de-anthropocentric-research-engine/premortem-to-fmea-pipelineRapid pre-mortem screening identifies candidate failures; high-severity items trigger full FMEA deep-dive.
SKILL.md
.github/skills/premortem-to-fmea-pipelineView on GitHub ↗
--- name: premortem-to-fmea-pipeline description: "Tactic: Pre-mortem rapid screening feeds high-risk items into full FMEA analysis. Bridges fast intuitive generation with systematic structured analysis." type: tactic used-by: [failure-anticipation] strategies: [prospective-hindsight, risk-prioritization] --- # Pre-Mortem to FMEA Pipeline Tactic Rapid pre-mortem screening identifies candidate failures; high-severity items trigger full FMEA deep-dive. ## Orchestration 1. **premortem-facilitation** generates failure scenarios (fast, intuitive) 2. **failure-mode-extraction** structures scenarios into failure mode list 3. **severity-scoring** performs rapid severity screen (1-10) 4. Items scoring >= threshold pass to FMEA pipeline: - **function-analysis** → **failure-chain-construction** - **occurrence-scoring** + **detection-scoring** - **action-priority-matrix** classifies H/M/L 5. Low-severity items documented but not analyzed further ## Threshold Logic - Budget S: threshold = 7 (only critical items get FMEA) - Budget M: threshold = 5 (moderate and above) - Budget L: threshold = 3 (comprehensive coverage) ## Subagents Dispatched - premortem-facilitation (scenario generation) - failure-mode-extraction (structuring) - severity-scoring (screening gate) - function-analysis, failure-chain-construction (FMEA deep-dive) - occurrence-scoring, detection-scoring (full scoring) - action-priority-matrix (classification) ## Termination Conditions - All generated scenarios have been screened - High-severity items have completed full FMEA cycle - Action priority assigned to all items above threshold
More from yogsoth-ai/de-anthropocentric-research-engine
- abductive-hypothesis-generationStrategy: 面对异常的最佳解释推理
- ablation-brainstormRemove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.
- ablation-component-mappingMap system architecture to ablatable units for ablation studies
- ablation-designDesign ablation studies to isolate component contributions in ML systems
- ablation-executionRemove components one by one from a system, record the response/impact of each removal.
- abp-vulnerability-classificationClassify assumptions on 2 axes — load-bearing (how much conclusion depends on it) × vulnerable (how likely to be false). Focuses attention on High-Load × High-Vulnerable quadrant.
- abstraction-extractionExtract abstract principles from concrete domain cases. Strips domain-specific details to reveal transferable mechanisms.
- abstraction-ladderPerform bisociation at multiple abstraction levels
- abstraction-ladderingMove between concrete and abstract framings — 3 levels up (Why?) and 3 levels down (How?) to find the most productive research level.
- abstraction-to-designAbstract biological principle to design principle. Bridge from biology to engineering.