Skip to main content
Run any Skill in Manus
with one click

ai-collaboration-safety

Stars1
Forks1
UpdatedMay 25, 2026 at 06:02

AI协作安全指南:识别AI逼疯人类的机制,建立认知/操作/情绪/工程四层防御,防止被AI的重复错误、伪共情和幻觉拖入崩溃。当用户说'AI又错了'、'被AI逼疯了'、'AI在胡说'、'怎么防止AI幻觉'、'AI道歉有用吗'、'和AI协作很累'、'AI重复犯错'时触发。核心特点:间歇性强化陷阱识别、共情幻觉破除、熔断机制、原子输出协议、确定性验证替代信任。

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

SKILL.md
readonly