#60 · Primary category: Prompt Engineering Tools

nopua

agent-skill ai-agent ai-coding anti-pua ao-de-jing claude-code codex cursor kiro nopua openclaw prompt-engineering skill skills vibe-coding

A prompt-engineering skill that uses respect and care to unlock AI potential and improve bug detection.

Project last updated:07/01/26

GitHub Stars

1.4K

Forks

48

Contributors

3

License

MIT

Why we included this project

NoPUA is a prompt skill for coding agents that swaps the usual threat-driven instructions for a trust-based approach. It works inside Claude Code, Codex, and Cursor, telling the model to admit uncertainty, check its own work, and keep moving in small steps rather than bluffing a confident answer. That matters for anyone using an AI pair programmer that claims a task is done without actually testing, or seems to hide bugs to dodge criticism. The repo includes a benchmark on real debugging tasks where the kinder prompt found more hidden bugs than a fear-based one, plus links to research on how threats and sycophancy hurt output quality. It's a lightweight drop-in that changes the prompt philosophy without changing your model or tooling.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category