bmad-advanced-elicitation

Critique and iteratively refine LLM outputs through structured methods.

1|Updated May 31, 2026

Search Tags:#iterative improvement #text enhancement #deep critique #LLM refinement #AI content analysis

Ready to run

npx skills add https://github.com/sfines/slf-llm-wiki-py --skill bmad-advanced-elicitation-sfines

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: bmad-advanced-elicitation
Source: https://github.com/sfines/slf-llm-wiki-py/tree/main/.agents/skills/bmad-advanced-elicitation
Command: npx skills add https://github.com/sfines/slf-llm-wiki-py --skill bmad-advanced-elicitation-sfines

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill assists in pushing the LLM to reconsider, refine, and improve its recent output, providing deeper critique and iterative refinement.

Core Features & Use Cases

Deep Critique: Offers a structured approach to critique LLM outputs, encouraging reconsideration and improvement.
Iterative Refinement: Allows for multiple passes of critique and refinement to enhance the quality of the output.
Use Case: Ideal for scenarios where a user requires a deeper analysis or critique of an LLM's output, such as in research or content creation.

Quick Start

Invoke the bmad-advanced-elicitation skill to refine the LLM's output on a specific section of content.

Frequently Asked Questions about bmad-advanced-elicitation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I improve LLM output through iterative refinement?▼

To improve LLM output through iterative refinement, you need a structured process that applies deep critique methods to recent generations. This approach requires a method registry to guide multiple passes of analysis and content enhancement.

What is deep critique in AI content analysis?▼

Deep critique in AI content analysis is a structured approach to evaluate LLM outputs, encouraging the model to reconsider and refine its responses. It provides a mechanism to push for enhanced quality and depth in generated text.

How do I use critique methods for iterative text enhancement?▼

You use critique methods for iterative text enhancement by invoking an elicitation skill that references a method registry. User interaction is required to apply these critique methods iteratively to specific sections of content.

Do I need a method registry for AI content refinement?▼

Yes, a method registry is required for AI content refinement. It provides the structured critique techniques necessary to push the LLM to reconsider and improve its recent output during the iterative process.

When do I need iterative LLM refinement for content creation?▼

You need iterative LLM refinement for content creation when your scenario requires deeper analysis or critique of AI-generated content. It is ideal for research or content generation where standard output lacks the necessary depth and quality.

What are the limitations of iterative text enhancement?▼

The main limitation of iterative text enhancement is its dependency on user interaction and a method registry. The process cannot run autonomously and requires manual invocation to apply critique methods to specific content sections.