hazalturkmen

LLMs In Practice For Students — AI skill for Claude Code

AI community

Practical LLM course for engineering students — prompt engineering, few-shot learning, chain-of-thought, and building agentic NLP pipelines with Claude Code.

How to install LLMs In Practice For Students

This entry records only its repository, not the path inside it, so there is no exact command to give. Open hazalturkmen/llms-in-practice-for-students and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What LLMs In Practice For Students does

Practical LLM course for engineering students — prompt engineering, few-shot learning, chain-of-thought, and building agentic NLP pipelines with Claude Code.

Alternatives in AI

AI Engineering Hub — In-depth tutorials on LLMs, RAGs and real-world AI agent applications 37.2k ★
Research Paper Writing Skills — Skill package for ML/CV/NLP paper writing, curated and adapted from Prof 1.5k ★
Auto Re Agent — Open-source AI reverse-engineering agent using Ghidra and LLMs to reconstruct and validate C/C++ functions fro 1.4k ★

README

LLMs in Practice — From Prompt to Pipeline

Hands-on course materials for computer engineering students. This course takes you from your first API call to building a fully autonomous NER pipeline using an AI agent — in two focused modules.

What you will learn

**Module 1 — Prompt Engineering** Understand how LLMs work and learn the techniques that make the difference between a prompt that kind of works and one that reliably produces the output you need.

**Module 2 — Agentic AI Coding** Move beyond the chatbox. Learn how agents work, how tools give models access to the real world, and how to use Claude Code to build a complete NLP project from scratch using only natural language.

Course structure

Module 1 — Prompt Engineering
├── 00_introduction.ipynb       — setup, API key, course overview
├── 01_getting_started.ipynb    — first API call, roles, get_completion helper
├── 02_prompting_tips.ipynb     — 5 essential tips every NLP engineer needs
└── 03_prompting_examples.ipynb — zero-shot, few-shot, chain-of-thought

Module 2 — Agentic AI Coding
└── Covered in the live classroom session using Claude Code CLI
    - What is an agent
    - The agent loop: perceive → plan → act → observe
    - Tool use and how models interact with the real world
    - CLAUDE.md: giving the agent memory
    - Live demo: building an NER pipeline from scratch

Prerequisites

Basic Python (functions, loops, dictionaries, working with JSON)
No prior NLP or AI experience required
No machine learning background needed

Stack

Tool	Purpose
Python 3.11	Language used throughout
OpenRouter	Unified API gateway — one key for all models
`openai` SDK	Client library (OpenRouter is OpenAI-compatible)
`python-dotenv`	Loading environment variables
`pytest`	Testing in Module 2