Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team
安装
npx skills add bmad-code-org/BMAD-METHOD --skill bmad-advanced-elicitationnpx skills add bmad-code-org/BMAD-METHOD --skill bmad-advanced-elicitation -a claude-code -gnpx skills add bmad-code-org/BMAD-METHOD --skill bmad-advanced-elicitation -a codex -ggemini skills install https://github.com/bmad-code-org/BMAD-METHOD.git --path skills/bmad-advanced-elicitationgh skill install bmad-code-org/BMAD-METHOD bmad-advanced-elicitationgit clone --depth 1 https://github.com/bmad-code-org/BMAD-METHOD /tmp/bmad-code-org__BMAD-METHOD
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/bmad-code-org__BMAD-METHOD/skills/bmad-advanced-elicitation ~/.claude/skills/bmad-advanced-elicitation # Claude Code
cp -R /tmp/bmad-code-org__BMAD-METHOD/skills/bmad-advanced-elicitation ~/.agents/skills/bmad-advanced-elicitation # Codex, Cursor, Gemini CLI, Copilot, OpenCode