skills.rest
oskrgab
oskrgabCOMMUNITY
Explore all skills by this author →
GitHub

caveman

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

11|2|Updated Dec 29, 2025
Search Tags:#communication style#token reduction#filler removal#concise writing#caveman mode#terse responses
One-click install
npx skills add https://github.com/oskrgab/petrodb --skill caveman-oskrgab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/oskrgab/petrodb/tree/main/.agents/skills/caveman
Command: npx skills add https://github.com/oskrgab/petrodb --skill caveman-oskrgab

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 switches the assistant into an ultra-compressed communication mode that cuts token usage by roughly 75% while keeping all technical substance intact. ## Core Features & Use Cases - Filler Elimination: Drops articles, pleasantries, hedging, and filler words while keeping code blocks, error messages, and technical terms exact. - Persistent Mode: 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 to get terse, high-signal answers like "Bug in auth middleware. Token expiry check use < not <=." instead of paragraph-length explanations. ## Quick Start Say "caveman mode" or "use caveman" to switch the assistant into terse, token-saving 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", "talk like caveman", "be brief", or "less tokens". The assistant then drops articles, filler, and pleasantries, cutting token usage by roughly 75% while keeping 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 turned off, so it will not revert on its own after a few 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, hedging, and pleasantries are removed.

When does caveman mode stop being terse automatically?▼

It temporarily switches to full clear sentences for security warnings, irreversible action confirmations like destructive SQL, multi-step sequences where fragment order could be misread, or when you ask for clarification. It resumes terse style afterward.

What are the limitations of ultra-compressed response styles?▼

Fragmented phrasing can be ambiguous for nuanced explanations, multi-step procedures, or safety-critical instructions. The skill handles this with an auto-clarity exception, but users needing detailed walkthroughs should stay in normal mode.

Related Skills

Explore More Content & Communication Skills→
hlbbbbbbbhlbbbbbbb
6

first-awakening

Guide initial AI assistant setup by prompting for a name and communication style.

Community
Basic
microsoftmicrosoft
9

dlm-diagnostics

Diagnose Microsoft Purview DLM issues in Exchange Online with PowerShell commands.

Official
Advanced
0xharryriddle0xharryriddle
3

context-compression

Generate probes and score context compression quality against a rubric.

Community
Advanced
JNRCHAYANJNRCHAYAN

caveman

Compresses assistant responses into terse, technically accurate language.

Community
Intermediate