Skills
.Work. You
Rest

caveman-skill

Community

Slash AI token costs 75% with caveman-style output

Software Engineering#cost reduction#token optimization#concise output#ai efficiency#output compression#caveman mode#input compression
Authorgaoqiongxie
Version1.0.0
Installs0

System Documentation

What problem does it solve?

High token consumption from verbose AI outputs drives up API costs and slows down workflows for frequent use cases like code reviews, document summarization, and long context loading, forcing users to pay for unnecessary extra tokens.

Core Features & Use Cases

  • Output Compression: Cuts response token usage by ~75% for code explanations, PRD summaries, and daily conversations without losing technical accuracy.
  • Input Compression: Reduces memory file size by ~46% for long context loads and CLAUDE.md files to free up context window space.
  • Sub-skills: Includes tools for generating one-line Git commit messages, one-sentence code reviews, and lifetime token savings tracking.
  • Use Case: If you regularly process large codebases, run frequent code reviews, or load long context files for development work, this skill cuts your AI costs while preserving all critical information.

Quick Start

Ask the AI to enable caveman mode to receive all subsequent responses in ultra-concise, low-token formatting.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: caveman-skill
Download link: https://github.com/gaoqiongxie/skills-ai/archive/main.zip#caveman-skill

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 536,000+ vetted skills library on demand.