Every AI agent works with a limited pool of attention. Context engineering helps you make the most of that resource. You learn to craft system prompts, tool definitions, and manage message history so the agent stays focused on what matters. The goal is to give the model the smallest set of high-signal tokens to get the job done right.
This skill covers the building blocks of context. You will understand system prompts that set the agent's behavior, tool definitions that list its actions, and retrieved documents that bring in knowledge only when needed. You also manage message history and tool outputs to keep context clean and efficient. Anyone who builds or works with AI agents can benefit from these practical techniques.
By mastering context engineering you avoid common pitfalls like vague instructions or bloated prompts. Your agents become more reliable, less confused, and better at completing complex tasks. This skill is essential for anyone who wants their AI tools to perform as intended.
Global
mkdir -p ~/.claude/skills/context-engineeringProject
mkdir -p .claude/skills/context-engineeringSource Repository
Cavemanjuliusbrussee/caveman
Talk like a smart caveman to save tokens without losing technical accuracy
Cavemanmattpocock/skills
Caveman mode for AI cuts token count 75% without losing technical accuracy
Enhance Promptgoogle-labs-code/stitch-skills
Turn vague UI ideas into clear, polished prompts with design system consistency
Humanizer Zhop7418/humanizer-zh
Remove AI writing patterns to make your text sound natural and human
Gws Modelarmorgoogleworkspace/cli
Filter harmful user content automatically with Google Model Armor for safety
Prompt Engineering Patternswshobson/agents
Master advanced prompt engineering patterns to get reliable and powerful AI outputs every time
Context Engineeringaddyosmani/agent-skills
Optimize your agent's context to improve output quality and focus
Writetw93/waza
Rewrite your prose to sound human and natural every time