constitutional-ai

Instructor is a structured output library that extracts validated data from LLM responses using Pydantic schemas. It automatically retries failed extractions and provides type-safe JSON parsing with streaming support. Use it when you need reliable, validated data extraction from LLMs like OpenAI or Anthropic.

NeMo Guardrails is a runtime safety framework for LLM applications that adds programmable guardrails. It provides key safety features like jailbreak detection, input/output validation, and hallucination detection using the Colang 2.0 DSL. Use it to enforce safety and compliance rules in production LLM deployments.

Constitutional AI trains models to be harmless using a two-phase method of self-critique/revision and reinforcement learning from AI feedback (RLAIF). It's designed for safety alignment, enabling models to reduce harmful outputs without relying on human labels. Developers can use this skill to implement the core safety system that powers Claude.

LlamaGuard is a specialized 7-8B parameter model from Meta for classifying LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and integrates with common deployment tools like vLLM and Hugging Face, as well as NeMo Guardrails. Use this skill to add a robust, dedicated moderation layer to filter unsafe content in your AI applications.