Applies a canonical 7-point meta-cognitive reasoning process (Discovery, Deconstruct, Diagnose, Develop, Deliver, Design, Debrief) to complex decisions. Produces structured outputs: answer, confidence score, and explicit caveats, plus verification checks and acceptance criteria. Useful for engineering tradeoffs, design decisions, and multi-factor analysis.
Use when a problem has multiple dependencies, tradeoffs, or unknowns and you need transparent confidence and rationale. Skip for simple fact queries or low-risk direct answers. Ideal for architecture decisions, policy choices, project scoping, and high-impact recommendations.
Inferred: Claude-style and other agents that support structured prompting and internal reasoning workflows (eg. Claude, Copilot/Code assistants, Cursor).
This skill has not been reviewed by our automated audit pipeline yet.