Safety and Alignment

Guidance for Constitutional AI, LlamaGuard, NeMo Guardrails, and Prompt Guard.

Parent repository GitHub

Type: skill category
Repository: Orchestra-Research/AI-Research-SKILLs
Readiness: Usable for guided research workflows, but framework guidance, autonomous claims, and demo results require project-specific validation
Keywords: 6

Location

Repository path

07-safety-alignment/

Invocation

Select Safety in the interactive installer, then ask a matching alignment or guardrail task.

Setup

Installation / activation

Safety filtering, guardrails, constitutional alignment, or prompt-defense tasks.

Keywords

safetyalignmentConstitutional AILlamaGuardNeMo GuardrailsPrompt Guard

Repository context

Orchestra-Research/AI-Research-SKILLs

MIT-licensed, cross-agent library of 98 stated SKILL.md research and engineering playbooks in 23 categories; for Claude Code it installs as individual or category skills and adds an autoresearch layer that routes literature, ideation, experimentation, analysis, artifact, and paper-writing work across domain skills.

AI researchMachine learning engineeringLarge language modelsModel trainingModel evaluationMechanistic interpretabilityInference and servingMLOps and infrastructureRetrieval-augmented generationMultimodal AIAI safety and alignmentScientific communication

Open full repository research