Get 22 prompt engineering techniques with tutorials for startup founders leveraging LLMs, backed by 7.6k+ GitHub stars.
intermediateโฑ 30 minutes๐ต Free
7,644 stars985 forksJupyter NotebookQuality 9/10Updated 6/17/2026100% free ยท open source
What it is
Learn 22 techniques for crafting effective instructions that supercharge AI tools.
What you can make with it
Automations like: asking Claude to create personalized product summaries from customer feedback.
How it helps
Prompt Engineering enables you to squeeze more value from LLMs like Claude, by teaching you how to design optimal prompts.
Real use case example
"A founder building a new conversational product wants to get the most out of Claude. They start by reading through the 22 prompt engineering techniques, then test out ' chaining multiple requests' to get a summary of customer feedback. After implementing this, they notice a 20% reduction in support requests."
If you're new
Beginners who want to start working with AI tools should pick this up, as it lays the groundwork.
If you're senior
Senior engineers and pros will reach for this as a reference when fine-tuning their Claude workflows.
Common confusion cleared up
This skill isn't about 'telling' Claude what to do, but rather crafting prompts that coax the most accurate and helpful output from it.
Best inside these AI tools
Claude DesktopClaude CodeClaude API
Pairs with
Claude APIJupyter Notebook
Why we list it on WorkflowStacks: This skill is here because it's a must-have foundation for working with AI tools, and it's free and open-source.
What it does
Provides 22 prompt engineering techniques with hands-on Jupyter Notebook tutorials to help startup founders effectively leverage Large Language Models (LLMs)
Install / run
Clone the repository using `git clone https://github.com/NirDiamant/Prompt_Engineering.git`
When to use it
โขWhen you need to optimize prompts for better LLM responses
โขWhen experimenting with different prompt engineering techniques to improve model performance
โขWhen seeking hands-on tutorials and examples for advanced LLM strategies
Quick start
1Open the cloned repository in a Jupyter Notebook environment
2Navigate to the `tutorials` directory and open a specific technique's notebook (e.g., `01_Fundamental_Concepts.ipynb`)
3Run the notebook cells to explore the technique and its implementation
4Modify the prompts and parameters in the notebook to experiment with different techniques
5Reference the `README.md` for an overview of the 22 techniques and tutorials available
Ready-to-paste prompt
Open `05_Primer_Prompt_Engineering.ipynb` and run the cell containing `prompt = 'Explain the concept of prompt engineering and its importance in LLMs.'` to see a primer on prompt engineering
Heads up: Ensure you have Jupyter Notebook installed and configured properly, as the tutorials are designed to be run in this environment, and some techniques may require specific LLM models or APIs to be effective
Saves to your device
Topics
ai
chain-of-thought
chatgpt
claude
few-shot-learning
genai
generative-ai
gpt
in-context-learning
langchain
llm
llms
machine-learning
openai
prompt-engineering
prompting
python
tutorials
What's inside โ free to inspect
No purchase needed
Read the entire source before you build โ unlike paid marketplaces that hide it behind a buy button.