Compresses AI responses by removing filler words while preserving technical accuracy.
npx skills add https://github.com/unnxt30/skills --skill caveman-unnxt30
Please help me install this Agent Skill. Skill: caveman Source: https://github.com/unnxt30/skills/tree/main/caveman Command: npx skills add https://github.com/unnxt30/skills --skill caveman-unnxt30
< not <=." instead of paragraph-length explanations. ## Quick Start Say "caveman mode" or "be brief" to switch the assistant into ultra-compressed responses for the rest of the conversation.High-intent search queries and answers about installing and using this skill.
Activate caveman mode by saying "caveman mode", "be brief", or "less tokens". The assistant then drops articles, filler words, and pleasantries, cutting token usage by roughly 75% while keeping technical content exact.
Say "stop caveman" or "normal mode" to deactivate it. The mode persists across every response until explicitly turned off, so it will not revert on its own after many turns.
No. Code blocks remain unchanged, error messages are quoted exactly, and technical terms stay precise. Only prose around the technical content is compressed into fragments.
It temporarily reverts to full sentences for security warnings, irreversible action confirmations, multi-step sequences where fragments risk misreading, or when you ask for clarification. It resumes caveman style afterward.
Fragmented phrasing can be harder to parse for nuanced explanations, onboarding documentation, or audiences unfamiliar with the topic. It is best suited for experienced users in fast technical back-and-forth, not polished written deliverables.
LayerDynamicsAnalyze code files to formulate targeted clarifying questions about scope and integration.
JerrylalalaSimplifies recent code changes using three parallel review agents while preserving behavior.
kaistenbergFetch, verify, and resolve GitHub PR review comments against actual code.
igoyetcheEnforce brevity and signal-over-noise in AI response generation.