Skip to main content

ai-collaboration-safety

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。

Jump to install

Source facts

Repository
gaoqiongxie/skills-ai
Last source activity
May 25, 2026 at 06:02
Detected SKILL.md language
Chinese
Stars
1
Forks
1

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.