Parallel multi-AI cross-validation research workflow (大版本). Dispatch N internal sub-agents + grok + gemini in parallel, automatically cross-validate findings, tier by confidence (strong consensus / partial / conflict / insufficient), generate tiered action items with arbitration. Use when user says "多 AI 调研", "交叉验证", "独立共识", "三脑调研", "multi-ai research", "parallel research", "cross-validate", or needs deep research that benefits from internal data + external 2026 consensus. NOT for quick factual Q&A, pure code reasoning, or tasks needing deep project context.
$npx -y skills add majiayu000/spellbook --skill multi-ai-researchInstalls into the current project.
Run `npx skills use "https://github.com/majiayu000/spellbook" --skill "majiayu000/spellbook/multi-ai-research"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/majiayu000/spellbook" that are relevant to the current task. Run `npx skills add "https://github.com/majiayu000/spellbook"` and select the relevant skills, then follow their instructions.