Enforce caveman-style brevity to reduce token usage in AI conversations.
npx skills add https://github.com/Charla-UTP/note --skill caveman-charla-utp
Please help me install this Agent Skill. Skill: caveman Source: https://github.com/Charla-UTP/note/tree/main/my-app/skills/caveman Command: npx skills add https://github.com/Charla-UTP/note --skill caveman-charla-utp
Ultra-compressed communication mode reduces token usage in AI interactions while preserving full technical accuracy.
Enable caveman mode and respond tersely while preserving technical accuracy.
High-intent search queries and answers about installing and using this skill.
You can reduce token usage by enabling caveman mode, which enforces ultra-compressed communication while preserving technical accuracy. It automatically triggers when you request token efficiency or say "talk like caveman".
Caveman mode activates when you say "caveman mode", "talk like caveman", "use caveman", "less tokens", or request token efficiency. It auto-triggers to deliver ultra-fast, terse responses without sacrificing correctness.
Token-efficient communication supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, and wenyan-ultra. These dictate the brevity and tone persistence applied to your technical outputs.
Yes, caveman mode works for technical debugging notes and explanations by enforcing brevity while preserving correctness. It applies structured rules across technical interactions to maintain accuracy in rapid decisions.
Avoid ultra-compressed communication mode when detailed, conversational explanations are required. It is designed for rapid decisions and debugging where terse output is valued, potentially reducing clarity for general audiences.
codenamevConfigure pragmatic mode with intensity levels, triggers, exemptions, and deferrals.
echowavesCompress technical responses into caveman-style terse communication modes.
JamesClonkCompress technical explanations into minimal words while preserving accuracy.
GanyuanRanTrim filler words while preserving technical terms and code blocks.
