bmad-advanced-elicitation

Apply structured multi-step elicitation to refine LLM output.

Updated Mar 18, 2026
One-click install
npx skills add https://github.com/AhmedKaram50/research --skill bmad-advanced-elicitation-ahmedkaram50
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bmad-advanced-elicitation
Source: https://github.com/AhmedKaram50/research/tree/main/shopify-builder/_bmad/core/skills/bmad-advanced-elicitation
Command: npx skills add https://github.com/AhmedKaram50/research --skill bmad-advanced-elicitation-ahmedkaram50

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Push the LLM to reconsider, refine, and improve its recent output by applying a structured, iterative elicitation workflow that exposes and corrects gaps in reasoning and quality.

Core Features & Use Cases

  • Iterative refinement: Systematically revises outputs through stepwise prompts and feedback loops to reach higher quality results.
  • Context-aware evolution: Maintains alignment with prior context while enhancing clarity, accuracy, and usefulness across drafts.
  • Use Case: Ideal for refining product explanations, technical docs, and promotional copy where precise language and robustness are essential.

Quick Start

Follow the workflow in ./workflow.md to iteratively refine and elevate the LLM's latest output.

Frequently Asked Questions about bmad-advanced-elicitation

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

FAQPage Schema
How do I iteratively refine LLM outputs for better quality?

Iteratively refine LLM outputs by applying a structured, multi-step elicitation workflow that pushes the model to reconsider and correct gaps, ensuring repeatable content improvements across drafts.

What is structured elicitation in prompt engineering?

Structured elicitation is a multi-step process that systematically revises LLM outputs through stepwise prompts and feedback loops, maintaining context awareness while enhancing clarity and accuracy.

Can I improve technical documentation using an iterative LLM workflow?

Yes, you can improve technical documentation using an iterative LLM workflow that applies structured elicitation to expose and correct gaps, ensuring precise language and robustness across drafts.

Does context-aware elicitation maintain alignment with prior conversation history?

Yes, context-aware elicitation maintains alignment with prior context while systematically revising outputs, ensuring the enhanced content evolves clearly and accurately without losing the original intent.

What is the best way to expose reasoning gaps in generated content?

The best way to expose reasoning gaps is to push the LLM to reconsider its recent output through a structured, iterative elicitation workflow that applies stepwise prompts and feedback loops.

When should I avoid using multi-step elicitation for prompt engineering?

Avoid multi-step elicitation when your task requires single-shot responses or when the overhead of iterative refinement outweighs the need for highly precise, robust document improvements.