caveman

Compress AI responses into terse caveman mode with selectable intensity levels.

Updated Feb 8, 2026

Search Tags:#technical writing #token efficiency #compression #caveman mode #prompt instructions #concise answers

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reduces AI response token usage while preserving technical accuracy by enforcing terse, “caveman mode” communication patterns.

Core Features & Use Cases

Ultra-compact responses: Drops filler, hedging, and articles while keeping technical terms exact.
Intensity control: Selects brevity levels including lite, full (default), ultra, and wenyan variants for stronger compression.
Safety-aware behavior: Avoids caveman style for security warnings, irreversible confirmations, and multi-step sequences where order can be misread.

Quick Start

Ask your AI to respond in caveman mode, for example: “Use caveman mode full and answer my question about why my function re-renders.”

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 AI responses while keeping technical accuracy?▼

Caveman mode compresses AI responses by dropping filler, hedging, and articles while keeping technical terms exact. This token efficiency technique maintains full technical accuracy during code troubleshooting and concept explanations.

What intensity levels can I select for concise AI prompt instructions?▼

Concise AI prompt instructions offer lite, full, ultra, and wenyan intensity levels. Full is the default compression mode, while ultra and wenyan variants apply stronger formatting rules for greater token reduction.

When should I avoid using compressed or caveman mode for AI answers?▼

Avoid compressed or caveman mode for security warnings, irreversible confirmations, and multi-step sequences where order can be misread. These safety-aware exceptions ensure critical clarity is maintained when technical accuracy alone is insufficient.

Does token compression work for code troubleshooting and technical concept explanations?▼

Token compression works for code troubleshooting and technical concept explanations by stripping unnecessary grammatical structures. It enforces terse communication patterns that reduce response size without altering the underlying technical meaning.

What is the best way to force an AI to drop filler words and give concise answers?▼

Force concise answers by explicitly requesting caveman mode in your prompt, such as asking the AI to use full or ultra intensity. This switches the AI to a compression mode that actively drops filler and enforces terse formatting.