Agent Skills: safety-alignment-llamaguard

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

ID: davila7/claude-code-templates/safety-alignment-llamaguard

Install this agent skill to your local

npx skills add davila7/claude-code-templates --skill safety-alignment-llamaguard

Skill Files

The files that make up safety-alignment-llamaguard.

Download Skill

More agent skills