Compress responses into terse, precise text to reduce token usage.
npx skills add https://github.com/Lutimi/claude2figma --skill caveman-lutimi
Please help me install this Agent Skill. Skill: caveman Source: https://github.com/Lutimi/claude2figma/tree/main/.cursor/skills/caveman Command: npx skills add https://github.com/Lutimi/claude2figma --skill caveman-lutimi
Ultra-compressed communication mode reduces token usage by delivering terse, precise responses without sacrificing technical accuracy.
Enable caveman mode by saying 'caveman mode' or '/caveman' and start conversing with minimal tokens.
High-intent search queries and answers about installing and using this skill.
To reduce token usage without losing technical accuracy, enable an ultra-compressed communication mode that delivers terse, precise responses across multi-turn conversations. This preserves technical substance while minimizing output length.
Available intensity levels for concise AI communication include lite, full, ultra, wenyan-lite, wenyan-full, and wenyan-ultra. These modes allow you to scale brevity based on your specific token-efficiency needs.
To switch to caveman mode for brief responses, simply say 'caveman mode' or type '/caveman' in your prompt. The system also auto-triggers on explicit token-efficiency requests or prompts to be brief.
Use ultra-compressed communication mode when brevity is valuable and efficiency matters in your multi-turn conversations. It is ideal for reducing token consumption while maintaining precise, technically accurate outputs.
Yes, concise communication mode supports auto-triggering on token-efficiency requests and user prompts to be brief. It applies explicit rules to automatically reduce token usage without requiring manual mode switching.
devendrapratapsinghDesign AI conversation memory systems with context window optimization and RAG.
vladpolewoiConverts AI responses to compressed technical text by removing filler words and articles while preserving precision.
JamesClonkCompress technical explanations into minimal words while preserving accuracy.
shllgRemove unnecessary words and fillers from technical discussions to reduce token usage.
