Last commit on April 10, 2026·Created on April 10, 2026
amanattar/caveman-claude-skill
“Reduces token consumption by stripping linguistic fluff while preserving technical precision.”
Combined rank
#549
across all skills
Stars
397
7d change unavailable
Forks
58
Watchers
6
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of real attention, adoption, and active maintenance.
TL;DR
This skill implements an ultra-compressed communication mode that removes articles, filler words, and pleasantries from AI responses. It is designed for users who prioritize token efficiency and brevity without sacrificing the accuracy of technical substance.
WHO IT'S FOR
AI agent power users
reducing token consumption for long conversations
Technical leads / architects
reviewing technical substance without conversational fluff
Chinese-speaking developers
using classical Chinese for extreme text compression
AI automation builders
optimizing LLM response latency and cost
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Want to install it?
Manual CopyRepository instructions