If your AI outputs feel weak or unreliable even after feeding it lots of data, you might be doing context stuffing instead of context engineering. Context stuffing means piling in every piece of information without thinking about what the AI really needs. Context engineering means carefully choosing and organizing the right information so the AI can focus on what matters.
This guide helps product managers spot the difference. You will learn how to build better memory and retrieval for AI agents. You will also fix common problems like Context Hoarding Disorder and use smart practices like bounded domains and episodic retrieval. The result is AI that consistently gives you high-quality answers without wasting time or money.
Global
mkdir -p ~/.claude/skills/context-engineering-advisorProject
mkdir -p .claude/skills/context-engineering-advisorSource 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