skills.rest
asarchami
asarchamiCOMMUNITY
Explore all skills by this author →
GitHub

caveman

Compresses AI responses by removing filler words while preserving technical accuracy.

1|2|Updated Nov 25, 2017
Search Tags:#communication style#token reduction#llm efficiency#terse output#concise responses#prompt mode
One-click install
npx skills add https://github.com/asarchami/dotfiles --skill caveman-asarchami
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/asarchami/dotfiles/tree/main/dot_config/opencode/skills/caveman
Command: npx skills add https://github.com/asarchami/dotfiles --skill caveman-asarchami

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long, verbose AI responses waste tokens and slow down reading when you only need the technical answer. This Skill cuts token usage by roughly 75% by stripping filler, articles, and pleasantries while keeping all technical substance intact. ## Core Features & Use Cases - Ultra-Compressed Responses: Drops articles, hedging, and pleasantries; uses fragments, abbreviations, and arrows for causality. - Persistent Mode: Stays active across every response once triggered, until you explicitly say "stop caveman" or "normal mode". - Auto-Clarity Exception: Temporarily reverts to full clarity for security warnings, destructive operations, and multi-step instructions where fragments could cause misreads. - Use Case: During a long debugging session, enable caveman mode to get terse, high-signal answers like "Bug in auth middleware. Token expiry check uses < not <=." instead of paragraph-long explanations. ## Quick Start Say "caveman mode" or "be brief" to activate ultra-compressed responses for the rest of the conversation.

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?▼

Activate caveman mode by saying "caveman mode", "be brief", or "less tokens". The assistant then drops articles, filler, and pleasantries, cutting token usage by roughly 75% while keeping all technical content exact.

How do I turn off caveman mode once it is active?▼

Say "stop caveman" or "normal mode" to deactivate it. The mode persists across every response until explicitly disabled, so it will not drift back to verbose output on its own.

Does caveman mode change code blocks or error messages?▼

No. Code blocks remain unchanged, technical terms stay exact, and errors are quoted verbatim. Only the surrounding prose is compressed into fragments and abbreviations.

When does caveman mode revert to full sentences automatically?▼

It temporarily drops compression for security warnings, irreversible action confirmations, and multi-step sequences where fragments risk misreading. Normal caveman style resumes immediately after the clear section.

What are the limitations of ultra-compressed AI responses?▼

Terse fragments can be harder to parse for beginners or in nuanced explanations. The mode is best for experienced users who want high-signal answers and already understand the technical context.

Related Skills

Explore More Content & Communication Skills→
jeffdevillejeffdeville

Example Skill

Automate skill activation when users mention trigger phrases in conversation.

Community
Basic
olimpus-softolimpus-soft

commitmsg

Generate commit messages from staged changes with branch and ticket ID.

Official
Advanced
darkmatterdarkmatter
1

caveman

Compress assistant replies into terse caveman-style language with configurable intensity levels.

Official
Basic
jonaspmjonaspm
39

caveman

Rewrite assistant responses into terse caveman-style prose with selectable intensity levels.

Community
Basic