Does it include fine-tuning guidance?

Absolutely. It offers structured workflows for preparing training data in JSONL format and managing fine-tuning jobs for modern LLMs.

How does it help with AI performance optimization?

It provides strategies for minimizing token usage, reducing latency through efficient prompting, and choosing the right model size for specific tasks.

What prompt techniques does this skill support?

It supports a wide range of advanced techniques including Zero-shot, Few-shot, Chain-of-Thought (CoT), Self-Consistency, and the ReAct (Reason + Act) pattern.

Can this skill help with RAG implementation?

Yes, it provides architectural guidance for Retrieval-Augmented Generation, including PostgreSQL/pgvector schemas, semantic chunking strategies, and embedding pipelines.

Prompt Engineer & LLM Specialist

Name: Prompt Engineer & LLM Specialist
Author: DonNigami

byDonNigami

0•

Data Science & ML

Architects advanced LLM prompts, RAG systems, and fine-tuning workflows to build production-grade AI applications.

This skill empowers Claude with the expertise of a world-class AI architect, focusing on the bridge between raw model capabilities and production-ready features. It provides structured guidance for complex prompt engineering techniques like Chain-of-Thought and ReAct, details robust Retrieval-Augmented Generation (RAG) architectures using vector databases, and outlines precise workflows for LLM fine-tuning. By implementing industry best practices for token optimization, safety guardrails, and semantic chunking, it helps developers build smarter, more efficient, and more reliable AI-driven software.

Key Features

01Advanced prompt engineering templates including Few-shot and Chain-of-Thought

02AI safety framework implementation and human-in-the-loop patterns

03RAG architecture design with vector database integration patterns

04Token cost optimization and latency reduction strategies

05Comprehensive LLM fine-tuning workflows and data preparation guides

060 GitHub stars

Use Cases

01Fine-tuning models for domain-specific data extraction and structured JSON output

02Developing a context-aware RAG system for internal documentation retrieval

03Optimizing complex logistics or reasoning tasks using recursive thinking patterns

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add donnigami/eddication.io prompt-engineer-llm

For use in Claude.ai and ChatGPT

Download Skill