Context Engineering

If you're writing system prompts or building agents, this is the reference for understanding what context actually is and how models process it. It breaks down the anatomy (system prompts, tool definitions, retrieved documents, message history, tool outputs) and explains why bigger context windows don't solve everything. The progressive disclosure principle alone is worth the read: load skill descriptions upfront, full content only when activated. Most useful when you're debugging why an agent is underperforming or trying to optimize token usage. Treats context as a finite attention budget rather than unlimited memory, which matches how these systems actually behave.

skills.sh installs: 1.5K
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add neolabhq/context-engineering-kit --skill context-engineering --agent claude-code

Installs into .claude/skills of the current project.

Files

Context Engineering Fundamentals

Context is the complete state available to a language model at inference time. It includes everything the model can attend to when generating responses: system instructions, tool definitions, retrieved documents, message history, and tool outputs. Understanding context fundamentals is prerequisite to effective context engineering.

Core Concepts

Context comprises several distinct components, each with different characteristics and constraints. The attention mechanism creates a finite budget that constrains effective context usage. Progressive disclosure manages this constraint by loading information only as needed. The engineering discipline is curating the smallest high-signal token set that achieves desired outcomes.

Detailed Topics

The Anatomy of Context

System Prompts System prompts establish the agent's core identity, constraints, and behavioral guidelines. They are loaded once at session start and typically persist throughout the conversation. System prompts should be extremely clear and use simple, direct language at the right altitude for the agent.

SKILL.md on GitHub