Safety Alignment skills
Free agent skills tagged safety alignment, ready to install into any SKILL.md-compatible agent.
3 skills
LlamaGuard
davila7
AI content moderation for safe interactions.
AI & AgentsintermediatePython · Shell30.2k repo
NeMo Guardrails
davila7
Enhance LLM safety with programmable runtime checks.
AI & AgentsintermediatePython · Shell30.2k repo
Constitutional AI
davila7
Train AI models to be harmless through self-critique.
AI & Agentsintermediate30.2k repo