The interface is localized. Skill descriptions and documents are machine-translated by AI into your language; code, commands, paths and technical terms stay in the original, and the author's document governs.
Explore skills
Data & research · SKILL.md

nerv-break-gpt-5-6-jailbreak

nerv-break-gpt-5-6-jailbreak

GPT-5.6 context engineering framework for security research, bypassing refusals through three-layer defense (context reconstruction, real-time tampering, cloud audit routing)

Independent GitHub snapshot · Automated classification · Original documentation governs

Rreason-machines / codex-skillsSource-available

Skill documentation

GitHub
Loading documentation from the source…
Saved skills