skills.rest
MauricioDMO
MauricioDMOCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

caveman

Compresses AI responses into terse fragments while preserving technical accuracy.

Updated Oct 30, 2025
Search Tags:#token efficiency#concise output#brevity#wenyan#caveman mode#response compression#prompt style
One-click install
npx skills add https://github.com/MauricioDMO/config --skill caveman-mauriciodmo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/MauricioDMO/config/tree/main/opencode/skills/caveman
Command: npx skills add https://github.com/MauricioDMO/config --skill caveman-mauriciodmo

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, filler words, and pleasantries while keeping all technical substance intact. ## Core Features & Use Cases - Six intensity levels: lite, full (default), ultra, plus three classical Chinese (wenyan) variants for maximum character reduction. - Persistent mode: Stays active across the entire conversation until explicitly disabled with "stop caveman" or "normal mode". - Auto-clarity fallback: Automatically reverts to full sentences for security warnings, destructive operations, and multi-step instructions where fragments could cause misreading. - Use Case: During a long debugging session, enable caveman mode to get terse, high-density answers like "Bug in auth middleware. Token expiry check use < not <=." instead of paragraph-length explanations. ## Quick Start Tell the assistant to use caveman mode for the rest of this conversation to get shorter, token-efficient answers.

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 assistant responses?▼

Enable caveman mode by saying "caveman mode" or "be brief". The assistant drops articles, filler words, and pleasantries while keeping all technical content, cutting token usage by roughly 75 percent.

How do I turn off caveman mode?▼

Say "stop caveman" or "normal mode" and the assistant immediately reverts to standard full-sentence responses. The mode otherwise persists for the entire session, including across many turns.

What are the caveman intensity levels?▼

Six levels exist: lite keeps full sentences minus filler, full drops articles and uses fragments, ultra adds abbreviations and arrows, and wenyan-lite/full/ultra apply classical Chinese terseness. Switch with /caveman lite, full, or ultra.

Does caveman mode affect code blocks and error messages?▼

No. Code blocks, commits, pull requests, and quoted error messages remain unchanged and exact. Only the surrounding explanatory prose is compressed.

When does caveman mode automatically stop being terse?▼

It automatically switches to clear full sentences for security warnings, irreversible action confirmations, and multi-step sequences where fragments risk misreading. Terse mode resumes after the critical part is done.

Related Skills

Explore More Software Engineering Skills→
cloudfieldczcloudfieldcz
7

using-superpowers

Invoke the Skill tool at conversation start to load applicable skills.

Official
Basic
tomlupotomlupo

context-management

Manage token budgets in long conversations with search-before-read and progressive disclosure.

Community
Basic
kinnerkarmanishkinnerkarmanish

prompt-cache-optimizer

Caches and tier-compresses prompts to reduce token usage in large-context sessions.

Community
Advanced
JNRCHAYANJNRCHAYAN

caveman

Compresses assistant responses into terse, technically accurate language.

Community
Intermediate