What problem does it solve? Long, filler-heavy AI responses waste tokens and slow down reading. This Skill compresses every model response into terse caveman-style prose, cutting output tokens by roughly 65% while keeping all technical details, code blocks, and error strings exact. ## Core Features & Use Cases - Six intensity levels: lite, full (default), ultra, plus three Classical Chinese (文言文) modes for extreme character reduction. - Persistent session mode: once activated, compression applies to every response until explicitly stopped with "stop caveman" or "normal mode". - Auto-clarity fallback: automatically reverts to normal prose for security warnings, irreversible-action confirmations, and ambiguous multi-step sequences. - Use Case: During a long debugging session, invoke /caveman to get direct, fragment-style answers like "Bug in auth middleware. Token expiry check use < not <=." instead of verbose explanations. ## Quick Start Say "caveman mode" or type /caveman to make all subsequent responses terse and token-efficient.
