Compresses AI responses by removing filler words while preserving technical accuracy.
npx skills add https://github.com/craft-ts/craft-ts --skill caveman-craft-ts
Please help me install this Agent Skill. Skill: caveman Source: https://github.com/craft-ts/craft-ts/tree/main/.agents/skills/caveman Command: npx skills add https://github.com/craft-ts/craft-ts --skill caveman-craft-ts
< not <=." instead of paragraph-length explanations. ## Quick Start Say "caveman mode" or "be brief" to activate 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, and pleasantries, cutting token usage by roughly 75% while keeping all technical content intact.
Say "stop caveman" or "normal mode" to revert to standard responses. The mode otherwise persists across every response in the conversation and does not drift back on its own.
No. Code blocks remain unchanged and error messages are quoted exactly. Only prose is compressed; technical terms, commands, and syntax stay precise.
It temporarily drops compression for security warnings, irreversible action confirmations, multi-step sequences where fragment order could be misread, or when you ask for clarification. It resumes terse mode afterward.
Fragmented phrasing can be harder to parse for nuanced explanations or unfamiliar topics. For learning new concepts or reviewing risky operations, standard mode is usually clearer.
tyl-99Formulate self-contained prompts for human experts on complex questions.
indoor47Diagnoses and fixes bugs from error messages or failing tests, then verifies solutions by rerunning them.
LsogodAnalyze compaction-debugger logs to quantify token savings per session.
SuperClaude-OrgCompresses AI output into bullet points and abbreviations to reduce token usage.