multi-model-orchestrator多模型编排系统，基于 oh-my-codex 框架。支持 deep-interview、ralplan、team、ralph、debug、frontend 等工作流模式。
docx-template-strictStrictly fill a DOCX template (preserving cover/headers/sections/styles) using placeholder tokens, with optional figures and references. For any task like: ‘...
pdf-visionExtract text content from image-based/scanned PDFs using multiple vision APIs with automatic fallback. Supports Xflow (qwen3-vl-plus) and ZhipuAI (GLM-4.6V-F...