Verified:GitHub

caveman

Compress conversational AI responses into caveman style with configurable intensity levels.

Updated Apr 19, 2026

Search Tags:#token-efficiency #mode-switch #caveman #prompt-safety #concise-communication #intensity-levels #ai-briefing

Ready to run

npx skills add https://github.com/NihaalManaf/LDR-Island --skill caveman-nihaalmanaf

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/NihaalManaf/LDR-Island/tree/main/.agents/skills/caveman
Command: npx skills add https://github.com/NihaalManaf/LDR-Island --skill caveman-nihaalmanaf

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ultra-compressed communication mode reduces token usage by enforcing caveman-style responses while preserving full technical accuracy.

Core Features & Use Cases

Keeps essential technical content while removing filler and fluff
Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra
Provides a persistent active mode to maintain caveman rules across turns

Quick Start

Enable caveman mode for subsequent responses to shorten output while preserving technical accuracy.

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 conversational AI without losing technical accuracy?▼

To reduce token usage without losing technical accuracy, enable a caveman-style communication mode that drops filler words and articles while preserving essential technical content. This ultra-compressed approach ensures brevity for rapid iteration and strict token budgets.

What intensity levels are available for concise communication modes?▼

Available intensity levels for concise communication include lite, full (default), ultra, wenyan-lite, wenyan-full, and wenyan-ultra. These modes enforce varying degrees of brevity while maintaining a persistent active mode to keep caveman rules applied across multiple conversational turns.

When should I use ultra-compressed responses for AI tasks?▼

Use ultra-compressed responses for AI tasks requiring strict token budgets, rapid iteration, or concise communication. This approach removes conversational fluff and drops articles, keeping only precise technical content needed for efficient processing and reduced latency.

Does the caveman mode maintain technical accuracy across multiple conversational turns?▼

Yes, caveman mode maintains technical accuracy across multiple conversational turns by using a persistent active mode. This enforces caveman-style rules continuously, dropping filler and articles while ensuring precise technical content is preserved throughout the entire interaction.

What is the difference between lite and ultra mode-switch intensity levels?▼

The difference between lite and ultra intensity levels lies in compression strictness. Lite provides moderate filler removal, while ultra enforces maximum brevity by aggressively dropping articles and filler, resulting in highly concise technical communication suitable for extreme token limits.