nopua
SolidThe 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.
Install
Quality Score: 80/100
Skill Content
Details
- Author
- sarenarococo641
- Repository
- sarenarococo641/nopua
- Created
- 4 months ago
- Last Updated
- yesterday
- Language
- Python
- License
- MIT
Similar Skills
Semantically similar based on skill content — not just same category
pua
This skill should be used when the user asks to "用PUA管AI", "高压督导AI", "让AI被骂后反省", "严格压AI执行", "PUA AI agent", or requests a no-excuse accountability mode where the AI agent accepts pressure, does not argue back, and immediately corrects mistakes.
ai-ux-patterns
The UX patterns that don't exist in deterministic software — confidence display, graceful failure, reversibility, human-in-the-loop, and progressive disclosure — for designing trustworthy probabilistic features. Grounded in Google PAIR (People + AI Guidebook) and Apple HIG for ML. Turns "how should the AI feature behave when it's unsure or wrong" from ad-hoc choices into a checklist.
fableit
Fable 5's blueprint for how to approach engineering problems; how to ground claims, reason toward a conclusion, design before coding, orchestrate sub-agents, hold a goal across long contexts, and verify work before reporting it. Load at the start of every project session, and whenever starting a nontrivial task, debugging, reviewing, or deciding how to build something.