Swing Mortem
Tvinger en Gary Klein pre-mortem: antag total fiasko, find derefter kvantificerede risici og flugtveje.
Testet · Virker
Hvad det gør
Udfører a structured 6-phase pre-mortem on a plan, architecture, or launch: generates exactly 5 specific failure scenarios (technical, organizational, external, temporal, assumption), ranks them on a likelihood x impact matrix, and defines measurable leading indicators and circuit-breaker triggers for the top 3. Udløses ved risk-analysis phrasing in English and Korean ('what could go wrong', '리스크 분석'); explicitly hands off to sibling skills for current-state review or option generation.
Testrapport
Kørte a real pre-mortem on this very testing batch and it correctly flagged the GitHub API rate-limit error we'd hit minutes earlier in-session as a quantified Technical failure scenario — the un-skilled baseline could only produce 'might have scaling issues' style generic bullets med no numbers or thresholds at all.
Testet: 2026-07-14 · Claude Code 2.x (agent harness)
Installation
git clone https://github.com/TheStack-ai/swing-skills cd swing-skills mkdir -p ~/.claude/skills cp -r skills/swing-mortem ~/.claude/skills/swing-mortem
Kommandoer og eksempelprompter
/swing-mortemTvinger en Gary Klein pre-mortem: antag total fiasko, find derefter kvantificerede risici og flugtveje.
Skills udløses af almindelige forespørgsler — ingen kommandoer at huske. Efter installationen aktiverer prompter som disse skillen (på engelsk):
Before we commit to this migration plan, what could go wrong?Do a pre-mortem on our Q3 launch plan with quantified risks.Assume this rollout totally failed, what are the top risk scenarios?