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 roughly 65-75% of output tokens while keeping all technical details, code, and error strings exact. ## Core Features & Use Cases - Six intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, and wenyan-ultra, ranging from light filler removal to extreme Classical Chinese compression. - Persistent session mode: once activated, the compressed style applies to every response until explicitly stopped or changed. - Auto-clarity fallback: automatically reverts to normal prose for security warnings, irreversible-action confirmations, and ambiguous multi-step sequences. - Use Case: A developer working through a long debugging session invokes /caveman ultra so every explanation arrives as compact fragments like "Inline obj prop → new ref → re-render. useMemo.", saving context window space. ## Quick Start Ask the AI to talk like caveman or invoke /caveman to enable compressed responses for the rest of the session.
