skills.rest
ferrarifankid04
ferrarifankid04COMMUNITY
Explore all skills by this author →
GitHub

caveman

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

Updated Aug 6, 2026
Search Tags:#communication style#token reduction#text compression#wenyan#concise responses#prompt mode
One-click install
npx skills add https://github.com/ferrarifankid04/ai-skills-public --skill caveman-ferrarifankid04
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/ferrarifankid04/ai-skills-public/tree/main/antigravity/caveman/plugins/caveman/skills/caveman
Command: npx skills add https://github.com/ferrarifankid04/ai-skills-public --skill caveman-ferrarifankid04

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 filler, articles, and pleasantries while keeping all technical substance, code, and error messages exact. ## Core Features & Use Cases - Six intensity levels: lite, full (default), ultra, plus wenyan-lite, wenyan-full, and wenyan-ultra for classical Chinese compression. - Persistent mode with safety overrides: Stays active across turns until told to stop, but automatically drops compression for security warnings, destructive operations, and ambiguous multi-step instructions. - Language preservation: Compresses style, not language — replies in Portuguese, Spanish, or Chinese stay in that language, and code, API names, and error strings remain verbatim. - Use Case: During a long debugging session, invoke /caveman to get terse answers like "Bug in auth middleware. Token expiry check use < not <=." instead of paragraph-length explanations. ## Quick Start Ask the assistant to use caveman mode to answer your technical questions briefly while keeping all code and error messages exact.

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?▼

Invoke caveman mode by saying "caveman mode", "be brief", or /caveman. The assistant drops articles, filler, and pleasantries while keeping code, technical terms, and error messages exact, cutting token usage by roughly 75%.

How do I change the caveman compression level?▼

Use /caveman lite, full, or ultra to switch intensity. Lite keeps full sentences without filler, full drops articles and uses fragments, and ultra abbreviates prose words and uses 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 and compresses only the style. It also offers wenyan-lite, wenyan-full, and wenyan-ultra levels that produce classical Chinese (文言文) responses with up to 90% character reduction.

When does caveman mode turn off automatically?▼

It drops compression for security warnings, irreversible action confirmations, ambiguous multi-step sequences, and when the user asks for clarification. It resumes caveman style after the clarity-critical part is done.

Does caveman mode change code blocks or error messages?▼

No. Code blocks, function names, API names, CLI commands, and exact error strings are always kept verbatim. Only prose is compressed; technical content stays exact at every intensity level.

Related Skills

Explore More Content & Communication Skills→
DaytimeBluesDaytimeBlues

behavioral-modes

Manage AI operational modes like brainstorm, implement, debug, and review.

Community
Intermediate
tDaliletDalile

caveman

Compress AI chat responses into caveman-style fragments to reduce token consumption.

Community
Intermediate
mifunedevmifunedev
28

caveman

Compress AI response prose while preserving code, API names, and commands.

Official
Advanced
JamkrisJamkris
86

token-budget-advisor

Estimate input tokens and select response depth before Gemini answers.

Community
Advanced