github:zechenzhangAGI/claude-ai-research-skills · first seen 2026-10-31 · source · badge
NVIDIA's runtime safety framework for LLM applications. Features: jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.