Use when you have an existing plan, design, or implemented code that needs adversarial review to find weaknesses, missing edge cases, and unnecessary complexity
Use when you want to autonomously improve a SKILL.md's quality by running iterative experiments. Triggers on "autoresearch 돌려줘", "스킬 품질 올려줘", "이 스킬을 자동으로 개선해줘", "run autoresearch on this skill", or any request to automatically improve a skill's eval pass rate through repeated experimentation. Applies Karpathy's autoresearch technique - fixed-budget iterative loop with single-metric hill-climbing and automatic keep/discard decisions.
Use when a developer needs to choose between two or more approaches during implementation. Triggers on "A vs B?", "should I use X or Y?", "which approach is better?", "Redis or Memcached?", "REST or gRPC?", "single table or split?", or any binary/multi-option technical decision. Use this skill whenever the user is weighing alternatives mid-implementation — even if they don't say "decide", if they're comparing approaches, this skill applies.
Use when creating implementation plans for complex multi-file features or architectural changes that benefit from multiple perspectives before implementation. Use this skill whenever the user asks to plan, design, or architect a feature that touches 3+ files, involves trade-offs between approaches, or would benefit from thinking through risks and requirements before coding. Even if the user says "plan this" without mentioning perspectives, this skill applies.
Multi-AI engineering loop orchestrating Claude, Codex, and Gemini for comprehensive validation. USE WHEN (1) mission-critical features requiring multi-perspective validation, (2) complex architectural decisions needing diverse AI viewpoints, (3) security-sensitive code requiring deep analysis, (4) user explicitly requests multi-AI review or triple-AI loop. DO NOT USE for simple features or single-file changes. MODES - Triple-AI (full coverage), Dual-AI Codex-Claude (security/logic), Dual-AI Gemini-Claude (UX/creativity).
Dual-AI engineering loop orchestrating Claude Code (planning/implementation) and Codex (validation/review). Use when (1) complex feature development requiring validation, (2) high-quality code with security/performance concerns, (3) large-scale refactoring, (4) user requests codex-claude loop or dual-AI review. Do NOT use for simple one-off fixes or prototypes.
OpenAI Codex CLI fundamentals for code analysis, review, and validation. Use when (1) executing codex commands for code review/analysis, (2) configuring models (gpt-5.3-codex/gpt-5.2/gpt-5.1-codex-max/gpt-5-codex-mini), sandbox modes (read-only/workspace-write), or reasoning effort (low/medium/high/xhigh), (3) managing Codex sessions with resume, (4) integrating Codex into automation scripts. Do NOT use for orchestration patterns (use codex-claude-loop instead).
C# code style and naming conventions based on POCU standards. Covers naming rules (mPascalCase for private, bBoolean prefix, EEnum prefix), code organization, C# 9.0 patterns. Use PROACTIVELY for C# code reviews, refactoring, or establishing project standards.