skills.rest
vinodkrishna221
vinodkrishna221COMMUNITY
Explore all skills by this author →
GitHub

caveman

Compresses AI responses into terse fragment-style output while preserving technical accuracy.

Updated Aug 23, 2026
Search Tags:#communication style#context efficiency#brevity#token compression#wenyan#terse responses
One-click install
npx skills add https://github.com/vinodkrishna221/Q-Trace --skill caveman-vinodkrishna221
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/vinodkrishna221/Q-Trace/tree/main/.agents/skills/caveman
Command: npx skills add https://github.com/vinodkrishna221/Q-Trace --skill caveman-vinodkrishna221

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long AI responses burn context window tokens and slow down reading during extended build sessions. This Skill cuts output tokens by roughly 65% by stripping filler, articles, 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. - Auto-clarity fallback: Automatically reverts to full sentences for security warnings, destructive operations, and ambiguous multi-step sequences, then resumes compression. - Language preservation: Compresses style without switching languages, keeping code, error strings, and technical terms verbatim. - Use Case: During a long debugging session, activate full mode so every response arrives as terse fragments like "Bug in auth middleware. Token expiry check use < not <=.", saving context for actual work. ## Quick Start Say "caveman mode" or "use caveman" to activate compressed responses, and say "stop caveman" or "normal mode" to revert.

Frequently Asked Questions about caveman

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

FAQPage Schema
How do I reduce AI response token usage in chat?▼

Activate caveman mode by saying "caveman mode" or "be brief". The skill strips articles, filler words, and pleasantries while keeping all technical content, cutting output tokens by roughly 65% at the default full level.

What intensity levels does caveman mode support?▼

Six levels: lite (no filler, full sentences), full (default, drops articles and uses fragments), ultra (maximum compression), and three wenyan variants that render responses in terse classical Chinese. Switch with /caveman lite, full, or ultra.

Does caveman mode work in languages other than English?▼

Yes, it preserves the user's dominant language and only compresses style. Portuguese input gets Portuguese caveman output, and the wenyan levels produce classical Chinese. Code, API names, and error strings always stay verbatim.

When does caveman mode stop compressing responses?▼

It automatically drops compression for security warnings, irreversible action confirmations, and multi-step sequences where fragments could cause misreading. Full sentences return for those parts, then caveman resumes afterward.

How do I turn off caveman mode?▼

Say "stop caveman" or "normal mode" to revert to standard responses. The mode otherwise persists across every response in the session and never drifts back on its own.

Related Skills

Explore More Content & Communication Skills→
mykaarmamykaarma

using-superpowers

Enforce applicable skill invocation before composing any response.

Official
Basic
OriginHubAIOriginHubAI
1

record-session

Archive work progress by reading history and updating the session log.

Official
Intermediate
SamuelSahaSamuelSaha

Token Optimization

Reduce AI token consumption via shallow skill loading, context pruning, and output compression.

Community
Intermediate
Charla-UTPCharla-UTP

caveman

Enforce caveman-style brevity to reduce token usage in AI conversations.

Official
Intermediate