Compresses AI responses into terse caveman-style phrasing to reduce token usage.
npx skills add https://github.com/MWest2020/skill-forge --skill caveman-mwest2020
Please help me install this Agent Skill. Skill: caveman Source: https://github.com/MWest2020/skill-forge/tree/main/skills/caveman Command: npx skills add https://github.com/MWest2020/skill-forge --skill caveman-mwest2020
< not <=." instead of paragraph-length explanations. ## Quick Start Tell the assistant 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.
Activate caveman mode by saying "caveman mode", "talk like caveman", or "be brief". The assistant then drops articles, filler words, and pleasantries, cutting token usage by roughly 75% while keeping technical content exact.
There are six levels: lite (no filler, full sentences), full (drop articles, fragments), ultra (abbreviations and arrows), and three wenyan variants using classical Chinese for maximum character compression. Switch with /caveman lite|full|ultra.
No. Code blocks, commits, pull requests, and quoted error messages stay unchanged and exact. Only the surrounding explanatory prose is compressed.
It temporarily drops the terse style for security warnings, irreversible action confirmations, and multi-step sequences where fragments could be misread, then resumes afterward. Saying "stop caveman" or "normal mode" disables it fully.
Yes. Once activated it stays active every response for the whole session, with no filler drift, until you explicitly say "stop caveman" or "normal mode" or the session ends.
Human-Frontier-Labs-IncPersist session memory and retrieve contextual patterns with AgentDB.
grojedaReduce token consumption by generating terse, technically accurate responses.
orochi-networkEncode knowledge, notes, and system prompts into compact KCL v0.1 documents.
danievanzylReduce token usage by removing filler words while preserving technical accuracy.