caveman

Compresses AI responses by removing filler words, articles, and pleasantries while preserving technical accuracy.

Updated Apr 16, 2025
One-click install
npx skills add https://github.com/damoke012/eks_code --skill caveman-damoke012
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/damoke012/eks_code/tree/main/.claude-env/skills/caveman
Command: npx skills add https://github.com/damoke012/eks_code --skill caveman-damoke012

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long, padded AI responses waste tokens and slow down reading when you only need the technical answer. This Skill enforces an ultra-compressed communication style that cuts token usage by roughly 75% while keeping all technical substance intact. ## Core Features & Use Cases - Terse Response Mode: Drops articles, filler words, hedging, and pleasantries; uses fragments, abbreviations, and arrows for causality. - Persistent Behavior: Stays active across every response once triggered, until the user explicitly says "stop caveman" or "normal mode". - Auto-Clarity Exception: Temporarily reverts to full sentences for security warnings, irreversible action confirmations, and multi-step sequences where fragments could be misread. - Use Case: During a long debugging session, activate caveman mode so every diagnosis and fix arrives as a compact, scannable fragment instead of a paragraph of preamble. ## Quick Start Ask the assistant to talk like caveman for the rest of this session, then continue asking your technical questions as usual.

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 less verbose?▼

Activate a terse communication mode that strips articles, filler words, and pleasantries while keeping technical content exact. The caveman skill does this persistently once triggered, cutting token usage by roughly 75% per response.

How to reduce token usage in long AI chat sessions?▼

Reduce token usage by instructing the model to drop filler, use fragments, abbreviate common terms like DB/auth/config, and express causality with arrows. This skill enforces that style automatically on every response until you say stop.

Does terse mode affect code blocks and error messages?▼

No. Code blocks remain unchanged and error messages are quoted exactly. Only the surrounding prose is compressed; technical terms stay precise so accuracy is never sacrificed for brevity.

When does caveman mode revert to normal language?▼

It temporarily switches to full clear sentences for security warnings, irreversible action confirmations, and multi-step sequences where fragments could be misread. It resumes terse style afterward, and fully turns off only when you say stop caveman or normal mode.

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

Fragmented phrasing can be ambiguous for nuanced explanations, onboarding documentation, or readers unfamiliar with the topic. It works best for experienced users in fast technical back-and-forth, not for polished written deliverables.