Advanced AI Skill: Refine Outputs with BMad Elicitation

Advanced AI Skill: Refine Outputs with BMad Elicitation

This advanced AI skill facilitates the refinement of outputs generated by AI coding agents like Claude Code, Cursor, and Codex. By employing a structured method, it allows users to request a deeper critique or refinement of the most recent AI-produced work by employing advanced elicitation techniques.

What this skill does

• Identifies and targets the most recent output in a conversation for refinement.
• Presents a menu of elicitation methods such as Socratic questioning, first principles analysis, pre-mortem evaluation, and red teaming.
• Applies the chosen elicitation technique(s) to refine and improve the AI’s output.
• Handles requests from both user prompts and other AI skills requesting refinement.
• Operates within the language context of the current session for seamless integration.
• Resolves customization preferences using the provided script, or defaults if initial resolution fails.

Who it is for

• Developers and technical teams seeking to enhance the quality and robustness of AI-generated outputs.
• AI specialists looking for systematic methods to critique and refine AI coding outputs.
• Organisations using AI for solution development that require iterative improvement processes.

Use cases

• A development team using Claude Code might pause a session to invoke this skill for refining a draft plan generated by an AI agent.
• An AI specialist wanting to apply a pre-mortem technique to anticipate potential flaws before finalizing a decision model.
• A coding trainer aiming to teach AI about iterative problem-solving by applying Socratic methods to a student's code output in a workshop.

Technical details

• Utilizes predefined scripts for method selection and customization resolution from the project and skill directories.
• Integrates seamlessly with AI application tools such as BMad Advanced Elicitation within the agent-skill framework.
• Configurable via `customize.toml` for workflow adaptability.
• Compatible with AI agents, including Claude Code, Cursor, and Codex, for enhanced skill integration.

Source & Licence

This package is built on open-source work published by 2233admin (2233admin/design-pipeline) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.