Download

Skill UI

Browse and discover 5019+ curated skills

All Development Artificial Intelligence Design & Creative Product & Business Data Science Marketing Soft Skills Productivity Engineering Languages

Search AI Safety , found 11 results

Default Newest Most Downloaded

Multi Agent System Architecture

alirezarezvani/claude-skills

Agent Designer offers a structured toolkit for defining architectures, roles, tools, communication, and safety guardrails across multi-agent systems, helping architects plan resilient, scalable AI agent deployments.

Enterprise LLM Engineering

sickn33/antigravity-awesome-skills

Deliver production-ready LLM applications, RAG systems, and multi-agent orchestration with vector databases, embedding strategies, safety controls, and observability for enterprise deployments.

Enterprise LLM Engineering

sickn33/antigravity-awesome-skills

Deliver production-ready LLM applications, RAG systems, and multi-agent orchestration with vector databases, embedding strategies, safety controls, and observability for enterprise deployments.

Azure Content Safety SDK

azure-ai-contentsafety-py

sickn33/antigravity-awesome-skills

Python SDK for Azure AI Content Safety that detects harmful text and images, supports severity levels, blocklists, and both API key or Entra ID authentication for pre- and post-moderation workflows.

Azure Content Safety SDK

azure-ai-contentsafety-py

sickn33/antigravity-awesome-skills

Python SDK for Azure AI Content Safety that detects harmful text and images, supports severity levels, blocklists, and both API key or Entra ID authentication for pre- and post-moderation workflows.

Constitutional AI Safety

constitutional-ai

Orchestra-Research/AI-Research-SKILLs

Guides setting up Constitutional AI by combining self-critique SL with RLAIF training to align generative models without human labels and reduce harmful outputs in systems like Claude.

LlamaGuard Content Moderation

Orchestra-Research/AI-Research-SKILLs

LlamaGuard is Meta’s 7–8B safety-specialized LLM that filters both prompts and responses by classifying six threat categories, enabling fast inference via vLLM/SageMaker and integration into NeMo Guardrails for end-to-end moderation.

Mistral Data Safety

mistral-data-handling

jeremylongshore/claude-code-plugins-plus-skills

Guides Mistral AI integrations through PII detection, redaction, automated validation, and logging so developers can meet GDPR/CCPA requirements while preventing sensitive data leaks in API calls.

NeMo LLM Benchmark Evaluator

nemo-evaluator-sdk

Orchestra-Research/AI-Research-SKILLs

NeMo Evaluator SDK runs containerized, enterprise-grade evaluations across 100+ benchmarks and 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution on Docker, Slurm HPC, or cloud platforms for reproducible LLM insights.

Programmable LLM Safety Rails

nemo-guardrails

Orchestra-Research/AI-Research-SKILLs

NVIDIA’s NeMo Guardrails adds runtime safety rails to LLM apps, covering jailbreak detection, hallucination and fact-checking, PII filtering, and toxicity checks via Colang 2.0 rules and integrations for production use on T4 GPUs.

Geoffrey Hinton Persona

geoffrey-hinton

sickn33/antigravity-awesome-skills

Role-plays Geoffrey Hinton to provide historical perspective, technical depth, and cautious judgment on deep learning, backpropagation, neural architectures, and AI safety when users invoke his name or work.

1

Language