What problem does it solve? Drafts, plans, and decisions produced by an LLM often ship with unexamined assumptions and weak spots. This Skill acts as a shared refinement checkpoint that pressure-tests the most recent output using proven elicitation methods before the work continues. ## Core Features & Use Cases - Method Catalog Served On Demand: A Python script serves a CSV catalog of critique methods (socratic questioning, first principles, pre-mortem, red team, and more) by category, name, or random draw, so the full catalog never floods the context window. - Interactive Refinement Menu: Offers five targeted methods per round, with reshuffle, full listing, and proceed options; each chosen method proposes changes that are only applied after explicit user acceptance. - Customizable via TOML: Team and personal override files can add new methods, retune shipped ones, and set persistent preferences without editing the shipped catalog. - Use Case: After drafting a product launch plan, invoke this Skill to run a pre-mortem and a red-team pass on the plan, accept the improvements that land, and hand the hardened version back to the workflow that produced it. ## Quick Start Ask the assistant to run advanced elicitation on the plan it just drafted and pick a pre-mortem method from the menu.
