ypollak2

Context Engineering Handbook — AI skill for Claude Code

AI community

The practitioner's guide to building effective context for AI agents and LLM applications.

How to install Context Engineering Handbook

This entry records only its repository, not the path inside it, so there is no exact command to give. Open ypollak2/context-engineering-handbook and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Context Engineering Handbook does

The practitioner's guide to building effective context for AI agents and LLM applications. 15 battle-tested patterns with Python + TypeScript code.

Alternatives in AI

README

Context Engineering Handbook

The practitioner's guide to building effective context for AI agents and LLM applications.

**35 patterns** | **7 categories** | **Python + TypeScript** | **Benchmarks** | **4 framework integrations**

[![GitHub Stars](https://img.shields.io/github/stars/ypollak2/context-engineering-handbook?style=flat&logo=github&label=Stars)](https://github.com/ypollak2/context-engineering-handbook/stargazers) [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE) [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md) [![Patterns](https://img.shields.io/badge/Patterns-35%20shipped-orange.svg)](#pattern-catalog) [![Python](https://img.shields.io/badge/Python-3.10+-3776AB.svg?logo=python&logoColor=white)](#examples) [![TypeScript](https://img.shields.io/badge/TypeScript-5.0+-3178C6.svg?logo=typescript&logoColor=white)](#examples)


Context engineering is the discipline of building the right information environment so an LLM can solve your actual problem. It was [named by Tobi Lutke](https://x.com/tobi/status/1925629163972653200) and [Andrej Karpathy](https://x.com/karpathy/status/1937902205765607626) in 2025, and it's quickly becoming the single most important skill in AI engineering.

**This is not another blog post or awesome-list.** This is a pattern catalog: 35 battle-tested patterns with runnable code, decision frameworks, and documented anti-patterns. Pick a problem, find the pattern, ship it.


Table of Contents