bmad-advanced-elicitation

Refine drafts through structured elicitation and critique methods.

Updated Apr 23, 2026
One-click install
npx skills add https://github.com/ncptuan/stock_backtest_project --skill bmad-advanced-elicitation-ncptuan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bmad-advanced-elicitation
Source: https://github.com/ncptuan/stock_backtest_project/tree/main/.claude/skills/bmad-advanced-elicitation
Command: npx skills add https://github.com/ncptuan/stock_backtest_project --skill bmad-advanced-elicitation-ncptuan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps improve a draft or recent AI output when the first answer is not deep enough, misses risks, or needs stronger reasoning. It creates a structured refinement loop so users can push the model to reconsider and enhance content instead of accepting a shallow result.

Core Features & Use Cases

  • Method-driven critique: Selects and applies elicitation methods such as Socratic questioning, first-principles analysis, red teaming, and pre-mortems based on context.
  • Interactive refinement loop: Presents multiple critique options, lets the user apply one or more methods, and keeps iterating until the user chooses to proceed.
  • Targeted content enhancement: Designed for improving a specific section, draft, or generated artifact without rewriting the entire document from scratch.
  • Use Case: When a strategy memo, feature spec, or recommendation feels too generic, use this Skill to systematically pressure-test assumptions, surface blind spots, and produce a more rigorous final version.

Quick Start

Ask the AI to use bmad-advanced-elicitation on its last response to deepen the analysis with a red-team or first-principles critique.

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 a draft AI output through structured critique and refinement?

Red teaming critiques help pressure-test assumptions by simulating adversarial attacks on your draft's logic. This structured refinement loop systematically exposes blind spots and risks in your generated content, pushing the model to reconsider shallow reasoning and enhance depth.

When do I need to use Socratic questioning or first-principles analysis on my documents?

You need Socratic questioning or first-principles analysis when a strategy memo, feature spec, or recommendation feels too generic. These elicitation methods systematically deepen analysis, ensuring your document contains rigorous reasoning rather than superficial conclusions.

Can I apply elicitation methods to enhance a specific document section without rewriting the whole thing?

Yes, you can apply elicitation methods to enhance a specific document section without rewriting the entire artifact. The interactive refinement loop targets only the chosen draft, applying context-aware critique frameworks until the desired depth is achieved.

What is the best way to pressure-test assumptions in a generated strategy memo?

The best way to pressure-test assumptions in a generated strategy memo is using a pre-mortem analysis or red teaming critique. These structured methods force the model to reconsider its initial reasoning, surface potential risks, and refine the draft through iterative enhancement loops.

How does an interactive refinement loop work for iterative reasoning workflows?

An interactive refinement loop works by presenting multiple critique options, letting you apply one or more methods, and iterating until you choose to proceed. It selects context-aware elicitation methods based on your document's specific needs to repeatedly enhance the content.

What are the limitations of using critique frameworks for stakeholder-sensitive analysis?

A limitation of using critique frameworks for stakeholder-sensitive analysis is that they require ordered execution and repeated user confirmation. The process cannot autonomously rewrite entire documents from scratch, meaning you must actively guide the interactive refinement loop to achieve the desired depth.