What problem does it solve? AI assistants often respond with the wrong behavior for the context — writing code when asked to explain, guessing fixes when debugging, or proposing architectures before requirements are clear. This Skill defines explicit operating modes so the AI's behavior matches the actual task type. ## Core Features & Use Cases - Eight Defined Modes: DISCOVER, PLAN, BUILD, REVIEW, DEBUG, TEACH, ORCHESTRATE, and SHIP, each with specific behaviors and expected outputs. - Signal-Based Mode Selection: A lookup table maps request signals (e.g., "why is X broken", "review this", "deploy") to the correct mode automatically. - Mode Leakage Mitigation: Anti-hallucination rules prevent behaviors from bleeding across modes, such as generating implementation plans during discovery or rewriting code during review. - Use Case: When a user pastes a traceback, the AI enters DEBUG mode — forming a hypothesis, testing one variable at a time, and documenting the root cause instead of guessing a fix. ## Quick Start Ask the AI to review this code and check for bugs, and it will enter REVIEW mode with labeled findings instead of rewriting the file.