Skill UI

Expertise in building production-grade LLM applications, advanced Retrieval-Augmented Generation (RAG) systems, and complex intelligent agents. This skill covers the entire AI lifecycle, including model orchestration, vector search optimization, multimodal integration (vision/audio), MLOps deployment, and robust safety governance for enterprise-level AI solutions.

Expertise in building production-grade LLM applications, advanced Retrieval-Augmented Generation (RAG) systems, and complex intelligent agents. This skill covers the entire AI lifecycle, including model orchestration, vector search optimization, multimodal integration (vision/audio), MLOps deployment, and robust safety governance for enterprise-level AI solutions.

A comprehensive toolkit for building production-grade AI agents focused on crypto business development. This skill guides users through the entire token listing lifecycle: autonomously discovering promising assets across multiple chains, applying a weighted 100-point scoring model, verifying safety via advanced wallet forensics, and managing outreach pipelines with necessary human oversight and LLM cascade patterns.

Instructor lets you shape LLM responses into validated Pydantic models, automatically retrying failed extractions, parsing complex JSON with type safety, and streaming partial outputs across Anthropic, OpenAI, and other providers.

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.

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.

A comprehensive toolkit designed to professionalize LLM prompt workflows. It moves prompts from ad-hoc drafts to measurable, production-ready assets through A/B testing against structured test cases, immutable version tracking, and governance guidelines. Essential for marketing teams needing verifiable quality and safety for AI-generated content.

This framework implements robust guardrails for LLM applications, validating both user inputs and model outputs. It detects prompt injection, sensitive PII (Personally Identifiable Information), toxic content, and ensures structured output compliance using advanced tools like NVIDIA NeMo Guardrails and Guardrails AI. Essential for building secure, reliable chatbots and RAG systems.

This comprehensive skill provides multi-layered guardrails for integrating with LLMs like Claude. It enforces security and compliance by implementing input validation (PII detection, length checks), system prompt restriction (scope control, safety rules), output filtering (preventing sensitive data leakage), cost governance, and model access policies. Ideal for building secure, robust, and governed AI applications.

Implements comprehensive runtime safety defenses for Large Language Model (LLM), RAG, and agent applications. This skill integrates industry-leading guardrail systems—including Llama Guard 3, NeMo Guardrails, and LLM Guard—to inspect and constrain all input and output data. It is essential for production environments requiring protection against adversarial attacks such as jailbreaks, prompt injection (OWASP LLM01), toxic content, and sensitive data leakage.

A comprehensive security skill designed to detect and mitigate indirect prompt injection attacks. It scans untrusted external content—including web pages, PDFs, and images—for hidden, obfuscated instructions before an LLM agent processes them. The pipeline combines content extraction (HTML, OCR), normalization, and dedicated ML models (e.g., LLM Guard, Prompt Guard 2) to ensure data safety.

NVIDIA garak is an open-source LLM vulnerability scanner designed for comprehensive red-teaming and security assessment. It systematically probes large language models (via OpenAI-compatible APIs, Hugging Face, etc.) using thousands of adversarial prompts. It covers critical vulnerabilities such as prompt injection, jailbreaking, data leakage, and toxicity. Use this tool to establish a repeatable security baseline before or after deployment, validate the effectiveness of safety guardrails, or generate quantitative evidence for AI risk assessments.