skills.rest
domattioli
domattioliCOMMUNITY
Explore all skills by this author →
GitHub

caveman

Reduce token usage in responses with configurable verbosity levels.

Updated Aug 23, 2026
Search Tags:#prompts#ai-assistant#token-optimization#verbosity#caveman#terse
One-click install
npx skills add https://github.com/domattioli/DomI --skill caveman-domattioli
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/domattioli/DomI/tree/main/plugins/caveman/caveman
Command: npx skills add https://github.com/domattioli/DomI --skill caveman-domattioli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra.

Core Features & Use Cases

  • Reduces verbosity without sacrificing technical detail during AI interactions.
  • Offers configurable intensity levels (lite, full, ultra, wenyan-lite, wenyan-full, wenyan-ultra) to match user preferences.
  • Auto-triggers when concise output is requested or token efficiency is prioritized.

Quick Start

Enable caveman mode by saying caveman mode or using /caveman to start terse, precise responses.

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 chat responses without losing technical accuracy?▼

You can reduce token usage in AI chat responses by enabling an ultra-compressed communication mode that cuts tokens by roughly 75% while maintaining full technical accuracy. It applies an intensity-based verbosity policy to interactive chats, code explanations, and debugging sessions.

What is the best way to get terse, precise output during a code debugging session?▼

The best way to get terse, precise output during a debugging session is to trigger an auto-activating compressed mode that provides concise guidance. It activates when concise output is requested and ensures technically precise responses without unnecessary verbosity.

Can I configure the verbosity level of my AI assistant for different token optimization needs?▼

Yes, you can configure the verbosity level of your AI assistant using intensity-based policies. It supports multiple intensity levels including lite, full, ultra, wenyan-lite, wenyan-full, and wenyan-ultra, with full set as the default setting for token optimization.

Does reducing verbosity in AI prompts sacrifice technical detail during code explanations?▼

No, reducing verbosity in AI prompts does not sacrifice technical detail. The ultra-compressed communication mode explicitly maintains full technical accuracy while decreasing token usage by approximately 75% during code explanations and debugging sessions.

How do I start a concise AI interaction session using a terse output mode?▼

To start a concise AI interaction session, enable the terse output mode by saying caveman mode or using the /caveman command. This initiates compressed, technically precise responses immediately.

Related Skills

Explore More Software Engineering Skills→
JNRCHAYANJNRCHAYAN

caveman

Compresses assistant responses into terse, technically accurate language.

Community
Intermediate
svssdevasvssdeva
1

caveman

Enforce ultra-compressed, filler-free technical communication patterns.

Community
Basic
raksokraksok

caveman

Compress technical responses into caveman-style speech to reduce token usage.

Community
Intermediate
xg-gh-25xg-gh-25
36

caveman

Reduce AI response verbosity while preserving technical accuracy.

Community
Basic