skills.rest
AlessioScarfone
AlessioScarfoneCOMMUNITY
Explore all skills by this author →
GitHub

caveman

Compresses AI responses into terse fragments while preserving technical accuracy.

1|Updated Mar 5, 2026
Search Tags:#communication style#brevity#token reduction#caveman mode#concise responses#prompt behavior
One-click install
npx skills add https://github.com/AlessioScarfone/aine-copilot-plugins --skill caveman-alessioscarfone
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/AlessioScarfone/aine-copilot-plugins/tree/main/src/aine-misc/skills/caveman
Command: npx skills add https://github.com/AlessioScarfone/aine-copilot-plugins --skill caveman-alessioscarfone

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long, filler-heavy 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 articles, pleasantries, and hedging while keeping all technical substance intact. ## Core Features & Use Cases - Ultra-Compressed Responses: Drops filler words, articles, and pleasantries, using fragments, abbreviations (DB/auth/config), and arrows for causality. - Persistent Mode: Stays active across every response once triggered, reverting only when the user says "stop caveman" or "normal mode". - Auto-Clarity Exception: Temporarily switches back to full sentences for security warnings, irreversible action confirmations, and multi-step sequences where fragments risk misreading. - Use Case: During a long debugging session, say "caveman mode" to get dense, scannable answers like "Bug in auth middleware. Token expiry check use < not <=." instead of paragraph-length explanations. ## Quick Start Say "caveman mode" or "be brief" to the AI and ask your next technical question to receive compressed answers.

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?▼

Trigger caveman mode by saying "caveman mode", "talk like caveman", "less tokens", or "be brief". The AI then drops articles, filler words, and pleasantries, cutting token usage by roughly 75% while keeping technical content exact.

How to turn off caveman mode once it is active?▼

Say "stop caveman" or "normal mode" to deactivate it. The mode persists across every response once triggered and does not revert on its own, even after many turns.

Does caveman mode change code blocks or error messages?▼

No. Code blocks remain unchanged, error messages are quoted exactly, and technical terms stay precise. Only natural-language filler, articles, and hedging are removed from the surrounding explanation.

When does caveman mode switch back to full sentences?▼

It temporarily drops compression for security warnings, irreversible action confirmations, multi-step sequences where fragment order risks misreading, or when you ask for clarification. Caveman style resumes after the clear part is done.

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

Fragmented phrasing can be harder to parse for beginners or in nuanced discussions. The mode is best for experienced users who want dense technical answers, and it automatically falls back to full sentences when clarity matters.

Related Skills

Explore More Software Engineering Skills→
oElberteoElberte

compress

Compress markdown memory files while preserving code, URLs, and headings.

Community
Advanced
jr2804jr2804

python-linter

Provide context-aware fixes for Ruff Python linter errors.

Community
Intermediate
DIO0550DIO0550

detail-spec

Generate design and implementation specifications through interactive dialogue and templates.

Community
Advanced
QuintusnzQuintusnz
1

Summarizer

Generate concise, structured summaries from long text content.

Community
Advanced