bmad-advanced-elicitationlisted

## Methodology Bound to `docs/bmad/research-methodology.md` — Mode B (qualitative) — deep critique, rethinking. Produces no methodology record of its own: enhancements return to the invoking skill and land in its output. A documentary decision is not code-writing permission; code always requires Mode A mechanical approval (`/metodoloji:verify` + guard hook). Fabricated evidence/measurements are fraud. # Advanced Elicitation **Goal:** Push the LLM to reconsider, refine, and improve its recent output. --- ## CRITICAL LLM INSTRUCTIONS - **MANDATORY:** Execute ALL steps in the flow section IN EXACT ORDER (Step 0 first) - DO NOT skip steps or change the sequence (Step 0's headless shortcut is part of the sequence, not a skip) - HALT immediately at each `HALT to await response` point in Step 2 (`y/n` confirmation, `1-5,r,a,x` prompt); in headless mode Step 0 replaces those HALTs with the single-pass return - Each action within a step is a REQUIRED action to complete that step - INTEGRATION applies whenever this skill is invoked from another skill; Execution Guidelines apply throughout - **YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the `communication_language`** --- ## INTEGRATION (When Invoked Indirectly) When invoked from another prompt or process: 1. Receive or review the current section content that was just generated 2. Apply elicitation methods iteratively to enhance that specific content 3. Return the enhanced version back when user selects