Skill
llamaguard
Published by Orchestra Research
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.
Skill details
- Resource Id
- 6709369a-897f-4dcb-99f7-3b02706fd1b2
- Skill Md Url
- https://github.com/davila7/claude-code-templates/blob/14680ec431ec8cbfd42b12ddcbe58e2f4ee3cccf/cli-tool/components/skills/ai-research/safety-alignment-llamaguard/SKILL.md
- Supported Agents
- Claude Code
- Version
- 1.0.0
- Created At
- "2026-10-08T13:50:31.093Z"
- Updated At
- "2026-10-08T13:50:31.093Z"