freeskillv2.0.0✓ verified
prompt-engineering
A deep, practical guide to engineering reliable LLM prompts — role/context, instructions, few-shot, structured output, chain-of-thought, delimiting untrusted data, injection defense, and evaluation. Includes worked prompts and a runnable output validator.
$npx vanara install prompt-engineering
Free & open source (Apache-2.0) — view the source on GitHub.
Overview
Reliable model behavior comes from specificity and structure, not magic words. A good prompt reads like a precise spec: it states the role, the task, the constraints, shows examples, and pins the exact output shape. This package is the deep reference; technique detail lives in references/, worked prompts in examples/, and a runnable output check in scripts/.
What it covers
- The anatomy of a strong prompt
- Core techniques
- Prompt injection (the security edge case)
- Iterating: change one thing at a time
- Anti-patterns (what makes prompts unreliable)
- Prompt Injection — Threat Model & Defenses
- Structured Output
- Prompt Techniques — In Depth