caveman

Compress responses to reduce token usage while preserving technical accuracy.

2|Updated Mar 3, 2026

Search Tags:#conciseness #token-optimization #prompt-engineering #caveman #technical-accuracy #terse-responses

Ready to run

npx skills add https://github.com/MomoDaviluke/star-citizen-promotion --skill caveman-momodaviluke

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/MomoDaviluke/star-citizen-promotion/tree/main/.agents/skills/caveman
Command: npx skills add https://github.com/MomoDaviluke/star-citizen-promotion --skill caveman-momodaviluke

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy.

Core Features & Use Cases

Ultra-compact responses with maintained technical substance.
Triggers on commands like /caveman or phrases like caveman mode.
Enforces rules to drop articles, filler, and pleasantries; uses abbreviations; uses concise syntax.
Use cases include rapid troubleshooting, code reviews, and high-volume chats with strict token limits.

Quick Start

Activate caveman mode by saying 'activate caveman' or invoking /caveman.

Frequently Asked Questions about caveman

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I reduce token usage in technical chats without losing accuracy?▼

To reduce token usage without losing accuracy, use an ultra-compressed communication mode that drops filler, articles, and pleasantries. This approach cuts token consumption by roughly 75% while maintaining full technical substance for rapid troubleshooting.

What is the best way to get concise responses for fast-paced code reviews?▼

The best way to get concise responses for code reviews is to activate a terse output mode. By enforcing rules to use abbreviations and concise syntax, it delivers high-density technical guidance tailored for fast-paced environments.

How do I activate caveman mode to compress prompt outputs?▼

To activate caveman mode and compress prompt outputs, simply say 'activate caveman' or invoke the /caveman command. This switches the model to an ultra-compact response style designed for strict token limits.

Does ultra-compact response mode work for high-volume technical chats?▼

Yes, ultra-compact response mode works for high-volume technical chats. It is specifically designed for environments with strict token limits, ensuring that rapid troubleshooting and code reviews remain accurate while minimizing verbosity.

When should I not use token-optimized terse responses?▼

You should not use token-optimized terse responses when context requires extensive explanations or conversational pleasantries. This mode aggressively drops articles and filler to compress responses, making it unsuitable for scenarios demanding standard conversational flow.