AI safety and content moderation. Includes Constitutional AI (self-improvement training), LlamaGuard (input/output moderation), and NeMo Guardrails (runtime safety with Colang DSL). Use when implementing safety filters, content moderation, or jailbreak detection.
/plugin marketplace add zechenzhangAGI/AI-research-SKILLs/plugin install safety-alignment@ai-research-skillsExpert guidance for Next.js Cache Components and Partial Prerendering (PPR). Proactively activates in projects with cacheComponents enabled.
Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)
Easily create hooks to prevent unwanted behaviors by analyzing conversation patterns
Frontend design skill for UI/UX implementation