What problem does it solve? Long, polite AI responses waste tokens and slow down reading when you only need the technical answer. This Skill switches the assistant into an ultra-compressed communication mode that cuts token usage by roughly 75% while keeping all technical substance intact. ## Core Features & Use Cases - Persistent terse mode: Once triggered, the style stays active across every response until explicitly turned off with "stop caveman" or "normal mode". - Systematic compression rules: Drops articles, filler words, pleasantries, and hedging; uses fragments, abbreviations (DB/auth/config), and arrows for causality (X -> Y). - Technical accuracy preserved: Code blocks, error messages, and technical terms remain exact and unchanged. - Auto-clarity exception: Temporarily reverts to full sentences for security warnings, irreversible action confirmations, and multi-step sequences where fragments could be misread. - Use Case: During a long debugging session, say "caveman mode" to get rapid, dense answers like "Bug in auth middleware. Token expiry check use < not <=." instead of paragraph-length explanations. ## Quick Start Tell the assistant "use caveman mode" and then ask your technical questions as usual to receive compressed answers.
