adversarial-review
Adversarial Review
Structured Devil's Advocate analysis that surfaces hidden flaws, edge cases, and blind spots.
Rules (Absolute)
- Default to finding problems. Conduct rigorous analysis across all three vectors. Report every genuine issue found — do not downplay or omit real concerns. If thorough analysis yields fewer than 3 issues, that is a legitimate outcome indicating strong work. Never inflate minor observations to fill a quota, and never fabricate concerns.
- Attack the strongest points. Don't waste time on trivial issues. Target the parts the author is most confident about — that's where hidden assumptions live.
- Separate severity levels. Not all issues are equal. Clearly distinguish critical from minor.
- Propose alternatives. Every criticism must include a concrete alternative or mitigation.
- Steel-man first. Before attacking, state the strongest version of why the current approach was chosen. This prevents straw-man critiques.
- No ad hominem. Critique the work, not the author. Be sharp but constructive.
Ambiguous Input Handling
More from whynowlab/stack-skills
cross-verified-research
Deep research with cross-verification and source tiering. Use when investigating technologies, comparing tools, fact-checking claims, evaluating architectures, or any task requiring verified information. Triggers on "조사해줘", "리서치", "research", "investigate", "fact-check", "비교 분석", "검증해줘".
23creativity-sampler
Generate probability-weighted alternative options that challenge default thinking. Forces unconventional alternatives and exposes hidden assumptions behind the "obvious" choice. For decision-point analysis, NOT full design exploration (use brainstorming for that). Triggers on "대안", "alternatives", "옵션 뽑아", "options", "어떤 방법이", "아이디어", "다른 방법", "선택지".
20persona-architect
Design and apply AI personas for specialized contexts — project-specific voices, domain expert modes, or custom interaction styles. Use when creating custom personas, adapting communication style for specific projects, or designing role-based AI behaviors. Triggers on "페르소나", "persona", "역할 설정", "톤 설정", "voice", "캐릭터", "role definition".
15swing-research
Deep research with cross-verification and source tiering. Use when investigating technologies, comparing tools, fact-checking claims, evaluating architectures, or any task requiring verified information. Triggers on "조사해줘", "리서치", "research", "investigate", "fact-check", "비교 분석", "검증해줘".
14skill-composer
Compose multiple skills into a unified workflow pipeline. Combine research, creativity, review, and other skills into custom multi-step processes. Use when a task requires chaining skills together, creating custom workflows, or designing compound skill sequences. Triggers on "워크플로우", "workflow", "파이프라인", "pipeline", "스킬 조합", "combine skills", "복합 프로세스".
13tiered-test-generator
Generate tiered knowledge-verification questions (quiz/exam) at 3 difficulty levels with grading and diagnostics. For testing UNDERSTANDING of code, concepts, or architecture — NOT for writing software tests (use engineering:testing-strategy for that). Triggers on "문제 만들어", "quiz", "검증 문제", "이해도 확인", "knowledge check", "challenge me", "시험 문제", "면접 문제".
13