Compresses AI responses by removing filler words while preserving technical accuracy.
npx skills add https://github.com/changfengpro/agent-skills --skill caveman-changfengpro
Please help me install this Agent Skill. Skill: caveman Source: https://github.com/changfengpro/agent-skills/tree/main/skills/caveman Command: npx skills add https://github.com/changfengpro/agent-skills --skill caveman-changfengpro
< not <=." instead of paragraph-length explanations. ## Quick Start Tell the AI to use caveman mode for the rest of this conversation to get shorter answers.High-intent search queries and answers about installing and using this skill.
Enable caveman mode by saying "caveman mode", "be brief", or "less tokens". The AI then drops articles, filler words, and pleasantries while keeping all technical content, code, and error messages exact.
Caveman mode cuts token usage by roughly 75% through fragment-style writing, abbreviations like DB/auth/config, and arrows for causality. Technical terms and code blocks remain unchanged, so accuracy is not affected.
Yes, caveman mode persists for every response once triggered and does not drift back to verbose output. It only turns off when the user explicitly says "stop caveman" or "normal mode".
It temporarily drops compression for security warnings, irreversible action confirmations, and multi-step sequences where fragments risk misreading. Full caveman style resumes immediately after the clarity-critical part is done.
No, code blocks remain completely unchanged and error messages are quoted exactly. Only the surrounding prose is compressed; technical terms stay precise and unaltered.
joshka0Assemble foxctl repository context for Gemini question answering.
ronniepinnellApply direct small edits to source files with automatic doc sync.
marinvchCompress long agent conversations into anchored structured summaries preserving session context.
JNRCHAYANCompresses assistant responses into terse, technically accurate language.