Context Window Management
sickn33/antigravity-awesome-skillsLarge language models have a limited memory called a context window. If you give them too much information, they can forget important details. This problem is known as context rot.
You can solve this by using smart strategies. Summarization condenses old messages into shorter forms. Trimming removes less important content. Routing picks the right approach based on how much memory is left. These methods help the model stay focused on what matters most.
This skill teaches you how to apply these techniques in your own projects. You will learn to count tokens, prioritize key context, and build prompts that use the beginning and end of the memory best. The goal is to keep your AI conversations clear and efficient.
Add Context Window Management skill to your workflow
Global
mkdir -p ~/.claude/skills/context-window-managementProject
mkdir -p .claude/skills/context-window-managementSource Repository
More Prompt Engineering & Context Engineering Claude Code Skills
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