skills.rest
kaitoartz
kaitoartzCOMMUNITY
Explore all skills by this author →
Website𝕏@kaitoartzzGitHub

caveman

Compresses AI responses into terse fragments while preserving technical accuracy.

Updated Jun 30, 2026
Search Tags:#token efficiency#context window#wenyan#caveman mode#response compression#prompt style#terse communication
One-click install
npx skills add https://github.com/kaitoartz/dotfiles --skill caveman-kaitoartz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/kaitoartz/dotfiles/tree/main/dot_gemini/config/skills/caveman
Command: npx skills add https://github.com/kaitoartz/dotfiles --skill caveman-kaitoartz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long, filler-heavy AI responses waste tokens and slow down reading. This Skill cuts token usage by roughly 75% by stripping articles, pleasantries, and hedging while keeping all technical substance intact. ## Core Features & Use Cases - Six Intensity Levels: Choose from lite, full (default), ultra, wenyan-lite, wenyan-full, and wenyan-ultra, including classical Chinese (文言文) compression modes. - Persistent Mode: Stays active across every response in a session until explicitly disabled with "stop caveman" or "normal mode". - Auto-Clarity Fallback: Automatically reverts to clear language for security warnings, irreversible action confirmations, and multi-step sequences, then resumes terse mode. - Use Case: During a long debugging session, enable full mode so every explanation arrives as compact fragments like "Bug in auth middleware. Token expiry check use < not <=", saving context window space. ## Quick Start Tell the AI to enable caveman mode by saying "use caveman mode" or invoking /caveman with your preferred intensity level.

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?▼

Enable caveman mode by saying "caveman mode", "talk like caveman", or invoking /caveman. It strips articles, filler words, and pleasantries while keeping technical terms and code blocks exact, cutting token usage by roughly 75%.

What intensity levels does caveman mode support?▼

Six levels: lite removes filler but keeps full sentences, full drops articles and uses fragments, ultra adds abbreviations and arrows, and wenyan-lite/full/ultra apply classical Chinese compression with up to 80-90% character reduction.

Does caveman mode affect code blocks and error messages?▼

No. Code blocks, commits, and pull requests remain written normally, and error messages are quoted exactly. Only the explanatory prose around them gets compressed.

When does caveman mode turn off automatically?▼

It temporarily drops terse style for security warnings, irreversible action confirmations, and multi-step sequences where fragments risk misreading, then resumes afterward. It fully turns off only with "stop caveman" or "normal mode".

Can caveman mode output classical Chinese?▼

Yes. The wenyan-lite, wenyan-full, and wenyan-ultra levels produce 文言文-style responses using classical sentence patterns and particles like 之, 乃, 為, and 其, achieving up to 90% character reduction.

Related Skills

Explore More Content & Communication Skills→
yocxy2yocxy2

plan-tune

Configure AI question sensitivity and interaction preferences in gstack.

Community
Advanced
GadaaLabsGadaaLabs
67

horizon

Monitor context health and compress stale reasoning during long sessions.

Community
Advanced
mscipiomscipio

token-tracker

Monitor AI model context window usage and warn before token overflow.

Community
Advanced
weipingweiping
1

voice-persona-venus

Route logistics voice queries to an executive-assistant persona for concise answers.

Community
Basic