skills.rest
jerrylin96
jerrylin96COMMUNITY
Explore all skills by this author →
WebsiteGitHub

caveman

Compresses AI responses into terse caveman-style output to reduce token usage.

9|Updated Jul 8, 2026
Search Tags:#communication style#compression#brevity#token reduction#terse output#prompt persona#chat assistant
One-click install
npx skills add https://github.com/jerrylin96/dotgemini --skill caveman-jerrylin96
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/jerrylin96/dotgemini/tree/main/skills/caveman
Command: npx skills add https://github.com/jerrylin96/dotgemini --skill caveman-jerrylin96

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long, filler-heavy AI responses waste tokens and slow down reading. This Skill enforces an ultra-compressed communication style that cuts output tokens by roughly 65% while preserving all technical substance. ## Core Features & Use Cases - Terse Output Mode: Drops articles, filler words, pleasantries, and hedging while keeping technical terms, code, and error strings exact. - Three Intensity Levels: Switch between lite (tight professional), full (classic caveman), and ultra (telegraphic) via /caveman lite|full|ultra. - Persistent Behavior: Stays active across every response until explicitly disabled with "stop caveman" or "normal mode". - Use Case: During a long debugging session where you want fast, dense answers, activate caveman mode so every reply strips fluff and keeps only the diagnosis and fix. ## Quick Start Ask the assistant to talk like a caveman or invoke /caveman to enable terse responses for the rest of the session.

Frequently Asked Questions about caveman

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

FAQPage Schema
How do I make AI responses shorter and use fewer tokens?▼

Activate caveman mode by saying "talk like caveman" or invoking /caveman. The assistant then drops articles, filler words, and pleasantries while keeping all technical content, cutting output tokens by roughly 65%.

How do I turn off caveman mode once it is active?▼

Say "stop caveman" or "normal mode" to disable it. The style persists across every response by design and will not revert on its own after multiple turns.

What are the caveman lite, full, and ultra intensity levels?▼

Lite removes filler and hedging but keeps full sentences. Full drops articles and uses fragments with short synonyms. Ultra is telegraphic with minimal words and heavy context assumptions. Switch with /caveman lite, full, or ultra.

Does terse mode change code blocks or error messages?▼

No. Code blocks, technical terms, API names, CLI commands, and exact error strings stay verbatim. Only the surrounding prose is compressed, so technical accuracy is preserved.

Does caveman mode work in languages other than English?▼

Yes. The style compresses the user's dominant language rather than forcing English. A Portuguese or Spanish user gets caveman-style replies in their own language, with technical terms kept untranslated.

Related Skills

Explore More Content & Communication Skills→
NVIDIANVIDIA
22.1k

nemoclaw-user-skills-coding

Expose NemoClaw documentation as discoverable skills for AI coding assistants.

Official
Basic
gonzalezpazmonicagonzalezpazmonica
47

headroom-optimization

Compress AI context windows using a 5-phase framework to reduce token usage.

Community
Intermediate
cagdotincagdotin
36

caveman

Remove filler words and articles from technical chat responses.

Community
Advanced
Sake-TeamSake-Team

token-budget-advisor

Modulate AI response depth and length according to token budgets.

Official
Intermediate