mh-advanced-elicitation

Iterative refinement of LLM output uses advanced critical analysis methods like socratic questioning and first principles to re-evaluate AI-generated content, improving decision-making quality through structured feedback and context-based method selection.

You can enhance AI assistant reasoning by applying critical analysis methods from a contextual registry, including socratic questioning, first principles, pre-mortem, and red team analysis, to iteratively evaluate and improve recent LLM output.

Applying pre-mortem and red team analysis to LLM-generated content involves invoking a critical analysis skill that re-evaluates recent AI output, selecting the appropriate method based on content analysis and contextual fit to enhance reasoning quality.

Yes, you can integrate user feedback into AI output refinement workflows; the system applies enhancements based on user decisions, ensuring the iterative critical analysis and refinement process aligns directly with user intent.

No, advanced elicitation requires no external dependencies to refine AI output, operating solely as an internal mechanism that selects critical thinking methods from a registry to iteratively enhance LLM-generated content.

You should use iterative critical analysis for LLM enhancement when you need to deeply reconsider and improve AI assistant decision-making, applying context-based method selection to refine output quality through structured feedback.