What problem does it solve? Drafts, plans, and decisions produced by an LLM often ship with unexamined assumptions and weak spots. This Skill provides a structured refinement checkpoint that pushes the model to reconsider and improve its most recent output using proven critique methods like socratic questioning, first principles, pre-mortem, and red teaming. ## Core Features & Use Cases - Method Catalog Serving: A Python script serves a CSV catalog of elicitation methods (categories, listings, random draws) without loading the whole catalog into context. - Interactive Refinement Menu: Presents five curated methods per round with reshuffle, list-all, and proceed options, applying chosen methods iteratively so refinements compound. - Customizable Workflow: A customize.toml file supports team and personal overrides for preferences and additional custom methods merged into the catalog. - Use Case: After drafting a product launch plan, invoke this Skill to run a pre-mortem and red team pass on the plan, then accept or reject each proposed change before finalizing. ## Quick Start Ask the assistant to run advanced elicitation on the plan it just drafted and pick a critique method from the menu.
