| Skill | Added | Review |
|---|---|---|
nopua codex/nopua/SKILL.md The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行'). ALL task types. Not for first failures. | 68 68 Impact — No eval scenarios have been run Securityby  Passed No findings from the security scan Version: bf4b2b6 | |
nopua skills/nopua/SKILL.md The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行'). ALL task types. Not for first failures. | 64 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: bf4b2b6 | |
nopua-zh skills/nopua-zh/SKILL.md The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行'). ALL task types. Not for first failures. | 64 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: bf4b2b6 | |
nopua-lite skills/nopua-lite/SKILL.md NoPUA Lite — core wisdom in ~1.5k tokens. Drives AI with trust and inner motivation instead of fear. Same Daoist philosophy, minimal footprint. For personal use and small-context models. | 53 53 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: bf4b2b6 | |
nopua SKILL.md The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行'). ALL task types. Not for first failures. | 56 56 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: bf4b2b6 |