edt-mcp-autopilot

【数据与研究】Autonomous, spec-driven, multi-agent pipeline that takes an EDT-MCP task or issue end-to-end — research → critics → architect → parallel development → review loop → tests → live-stand check → Russian issue comment + PR. Use when asked to take a whole task/issue to completion autonomously (not for a single quick edit or a pure question).

独立 GitHub 快照 · 自动分类 · 以原作者文档为准