quality-critic

Adversarial validation for all stages. Detects fabrications, identifies analytical flaws, challenges assumptions, makes approval decisions. Seeks problems rather than confirming quality. Does NOT complete deliverables or fix issues.

$ 설치

git clone https://github.com/ensingm2/AI-threat-modeling-rulesets /tmp/AI-threat-modeling-rulesets && cp -r /tmp/AI-threat-modeling-rulesets/.ai-instructions/skills/quality-critic ~/.claude/skills/AI-threat-modeling-rulesets

// tip: Run this command in your terminal to install the skill