think

Use when something needs to be designed or built and the shape of the solution isn't clear yet. Triggers on: "어떻게 만들지?", "기능 설계해줘", "아키텍처 잡아줘", "뭘 어떻게 구현해야 해?", "design this feature", "how should we build X?", "새 서비스 어떻게 시작하지?". Best for: new features, tools, systems, or products without a spec yet. Not for: bug fixes, changes to already-designed things, or when the problem itself keeps resisting (use problem-reframer) — or when scattered ideas need organizing (use thought-organizer).

Use when facing a choice between options where the trade-offs aren't obvious. Triggers on: "A vs B 뭐가 나아?", "어떤 걸 써야 해?", "build vs buy", "이 아키텍처 괜찮아?", "Redis vs Postgres", "어떤 DB 골라야 해?", or any "should we adopt X?" question. Best for: technology selection, architecture decisions, irreversible investments. Not for: decisions already made (post-hoc justification), or trivially obvious choices.

Use when you need to think through a complex problem systematically — generating ideas, stress-testing them, and converging on a decision. Triggers on: "think workflow", "깊이 있게 생각해보자", "아이디어를 체계적으로 검토", "structured thinking", "체계적 사고 프로세스", "idea to decision". Best for: strategy decisions, architecture choices, hard tradeoffs, or any situation where you need to diverge before you converge. Not for: quick answers, factual lookups, or already-decided actions.

Use when someone wants their idea, plan, or decision stress-tested with the strongest possible objections. Triggers on: "반론 던져줘", "약점 찾아줘", "이 계획 문제점이 뭐야?", "devil's advocate 해줘", "결함 찾아줘", "비판해줘", "이 아이디어 왜 틀렸어?", "steel-man the opposite view", "반대 의견 강하게 말해줘", "치명적 약점이 뭔지 알고 싶어". Best for: pre-commitment stress testing, finding fatal flaws, adversarial design review. Not for: balanced pro/con analysis or improvement help — this is adversarial critique only.

Use when the current approach feels fundamentally wrong, inherited constraints need questioning, or someone wants to reason from the ground up. Triggers on: "왜 이렇게 해야 해?", "기본부터 다시 생각해", "first principles", "가정을 의심해봐", "이 방식 자체가 맞는 건지", "처음부터 다시 설계하면?", "why does it have to be this way?". Best for: cost-reduction challenges, architectural redesigns, questioning inherited constraints. Not for: routine decisions where existing solutions already work — reserve for novel situations.