caveman

Compress AI-generated text responses to reduce token usage.

7|Updated Oct 20, 2025

Search Tags:#communication #efficiency #compression #text reduction #caveman mode

Ready to run

npx skills add https://github.com/borkweb/skills --skill caveman-borkweb

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/borkweb/skills/tree/main/skills/core/caveman
Command: npx skills add https://github.com/borkweb/skills --skill caveman-borkweb

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill reduces the number of tokens used in responses, allowing for more concise and efficient communication while maintaining technical accuracy.

Core Features & Use Cases

Ultra-Compression: Cuts token usage by 75% while preserving technical accuracy.
Intensity Levels: Offers different levels of compression (lite, full, ultra, and wenyan variants).
Use Case: When a user requests "caveman mode" or needs to save tokens, this Skill can be activated to provide brief, to-the-point responses.

Quick Start

Enter "caveman mode" to enable ultra-compressed communication.

Frequently Asked Questions about caveman

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

FAQPage Schema

How do I reduce the token count in AI generated text responses?▼

To reduce the token count in AI generated text responses, you can apply text compression techniques that prioritize brevity over verbosity while preserving technical accuracy. This approach cuts token usage by up to 75% for efficient communication.

What is text compression for technical support and documentation?▼

Text compression for technical support and documentation is the process of condensing AI responses to essential points. It maintains technical accuracy while eliminating verbosity, making it ideal for briefings and support scenarios where brevity is valued.

Can I adjust the intensity level of text reduction for different tasks?▼

Yes, you can adjust the intensity level of text reduction. The skill offers multiple compression variants including lite, full, ultra, and wenyan levels, allowing you to choose the exact balance of brevity and detail needed for your specific task.

Do I need a specific model to generate compressed text effectively?▼

Yes, you need a model capable of understanding and generating compressed text to use this text reduction technique effectively. The model must accurately interpret compression instructions and output essential points without losing technical accuracy.

When should I not use ultra-compression for AI communication?▼

You should not use ultra-compression for AI communication when verbosity, conversational tone, or detailed explanations are required. Since it reduces tokens by 75% to deliver essential points, it may remove context needed for general or casual interactions.