skills.rest
KinalVR-Expo2026
KinalVR-Expo2026OFFICIAL
Explore all skills by this author →
GitHub

caveman

Compresses AI responses into terse caveman-style prose while preserving technical accuracy.

Updated May 26, 2026
Search Tags:#token efficiency#token compression#classical chinese#caveman mode#terse responses#verbosity control
One-click install
npx skills add https://github.com/KinalVR-Expo2026/KinalVR-Client --skill caveman-kinalvr-expo2026
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/KinalVR-Expo2026/KinalVR-Client/tree/main/.claude/.agents/skills/caveman
Command: npx skills add https://github.com/KinalVR-Expo2026/KinalVR-Client --skill caveman-kinalvr-expo2026

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long, verbose AI responses waste tokens and slow down reading. This Skill cuts output token usage by roughly 65-75% by stripping filler, articles, and pleasantries while keeping every technical detail, code block, and error string exact. ## Core Features & Use Cases - Six intensity levels: lite, full (default), ultra, plus three Classical Chinese (文言文) variants for maximum character reduction. - Persistent session mode: once activated, the compressed style applies to every response until explicitly stopped. - Auto-clarity fallback: automatically reverts to normal prose for security warnings, irreversible-action confirmations, and ambiguous multi-step instructions. - Use Case: During a long debugging session, enable full mode so every explanation arrives as terse fragments like "Inline obj prop → new ref → re-render. useMemo.", cutting reading time without losing precision. ## Quick Start Ask the AI to talk like caveman or invoke /caveman to start receiving ultra-compressed 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 reduce token usage in AI chat responses?▼

Enable caveman mode by saying "talk like caveman" or invoking /caveman. It strips articles, filler, and hedging from every response, cutting output tokens by roughly 65-75% while keeping code and error strings exact.

How do I change the compression level of caveman mode?▼

Use /caveman lite, full, or ultra to switch intensity. Lite keeps full sentences, full drops articles and uses fragments, and ultra adds abbreviations and arrows for causality. The level persists until changed or the session ends.

Does caveman mode work in languages other than English?▼

Yes, it preserves the user's dominant language, compressing style rather than translating. It also offers three Classical Chinese (文言文) levels for 80-90% character reduction. Technical terms, code, and error strings always stay verbatim.

When does caveman mode stop compressing responses?▼

It automatically drops to normal prose for security warnings, irreversible-action confirmations, ambiguous multi-step sequences, and repeated questions. Saying "stop caveman" or "normal mode" turns it off entirely.

Does caveman mode affect code blocks and error messages?▼

No. Code blocks, function names, API names, CLI commands, and exact error strings are never abbreviated or altered. Only surrounding prose is compressed, so technical content remains fully accurate.

Related Skills

Explore More Software Engineering Skills→
TrayMachiTrayMachi

caveman

Compresses model responses into terse caveman-style prose while preserving technical accuracy.

Community
Basic
hksloverhkslover
47

trellis-update-spec

Capture debugging lessons and design decisions into code-spec documentation.

Community
Intermediate
gonzalezpazmonicagonzalezpazmonica
47

headroom-optimization

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

Community
Intermediate
smykla-skalskismykla-skalski
3

promptgen

Generate optimized AI prompts from rough instructions for Claude or GPT.

Official
Advanced