What is the LLM Specialist skill?

It is a meta-skill for Claude Code that routes your requests to specialized sub-skills for prompt engineering, fine-tuning, RAG, evaluation, and safety.

Can this skill improve model latency?

Yes, it includes specialized routing for inference optimization, covering topics like quantization, batching, and KV cache optimization.

Does it provide help with LLM safety?

Yes, it offers patterns for preventing prompt injection, detecting jailbreaks, and implementing guardrails to reduce hallucinations.

How does it help with RAG systems?

The skill provides guidance on architecture, chunking strategies, retrieval methods, and evaluation metrics specifically for Retrieval-Augmented Generation.

LLM Engineering Specialist

Name: LLM Engineering Specialist
Author: tachyon-beep

bytachyon-beep

•

데이터 과학 및 ML

Guides and routes LLM-related development tasks toward specialized patterns for prompt engineering, RAG, fine-tuning, and model optimization.

소개

The LLM Engineering Specialist skill acts as a central hub for advanced AI development, providing structured guidance on the entire lifecycle of Large Language Model integration. It helps developers navigate complex decisions like choosing between RAG and fine-tuning, optimizing inference speeds, managing token-heavy context windows, and implementing robust safety guardrails. By routing to specific, battle-tested patterns, it ensures that Claude applies the most effective strategies for building, evaluating, and deploying production-grade LLM applications.

주요 기능

5 GitHub stars
Intelligent routing for specialized LLM engineering tasks
Prompt engineering and instruction optimization patterns
RAG architecture and retrieval strategy guidance
Fine-tuning strategy selection including LoRA and QLoRA
Inference optimization and safety alignment guardrails

사용 사례

Architecting a high-performance RAG system for private documentation
Optimizing model latency and throughput for production-scale inference
Implementing comprehensive evaluation metrics for LLM output quality

소개

주요 기능

5 GitHub stars
Intelligent routing for specialized LLM engineering tasks
Prompt engineering and instruction optimization patterns
RAG architecture and retrieval strategy guidance
Fine-tuning strategy selection including LoRA and QLoRA
Inference optimization and safety alignment guardrails

사용 사례

Architecting a high-performance RAG system for private documentation
Optimizing model latency and throughput for production-scale inference
Implementing comprehensive evaluation metrics for LLM output quality