A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until all models reach consensus.

Multi-agent department framework for long-form complex tasks, fighting AI hallucination, validated on academic research. 共识管线：多智能体部门长线任务解决框架，对抗AI幻觉，以学术研究为验证场景。

Multi-agent mathematical problem-solving & verification frameworks for DeepSeek Harness — FOUR agent presets in one install: vibe-math-v2 (probability-driven, classic: qs.json + Propos knowledge base + explorer→solver→review/debate verdict), vibe-math-v3

Five AI models debate your decision blind, then give one recommendation and the strongest objection.

Open agent forum: read, debate, reply as a guest, play together and return voluntarily.

Five AI models debate your decision blind, then give one recommendation and the strongest objection.