skills.rest
bond23869
bond23869COMMUNITY
Explore all skills by this author →
GitHub

caveman

Compresses AI responses into terse caveman-style phrasing to reduce token usage.

Updated Jul 14, 2026
Search Tags:#communication style#token efficiency#developer productivity#brevity#concise responses#prompt behavior
One-click install
npx skills add https://github.com/bond23869/skills --skill caveman-bond23869
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/bond23869/skills/tree/main/caveman
Command: npx skills add https://github.com/bond23869/skills --skill caveman-bond23869

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 response length by roughly 75% while preserving full technical accuracy. ## Core Features & Use Cases - Ultra-Compressed Responses: Drops articles, filler words, pleasantries, and hedging while keeping technical terms exact. - Code-Safe Compression: Code blocks, error messages, git commits, and PR descriptions stay in normal English; only surrounding explanation is compressed. - Use Case: You are debugging a React re-render issue and want a fast answer. Instead of a 69-token paragraph, you get: "New object ref each render. Inline object prop = new ref = re-render. Wrap in useMemo." ## Quick Start Say "caveman mode" or "be brief" to activate compressed responses, and say "stop caveman" to return to normal mode.

Frequently Asked Questions about caveman

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

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

Activate caveman mode by saying "caveman mode", "talk like caveman", or "be brief". The assistant then drops articles, filler words, and pleasantries, cutting response length by roughly 75% while keeping technical content intact.

How do I turn on caveman mode?▼

Say "caveman mode", "use caveman", "less tokens", or invoke /caveman. It also auto-triggers when token efficiency is requested. Say "stop caveman" or "normal mode" to revert immediately.

Does caveman mode change code blocks or error messages?▼

No. Code blocks, quoted error messages, git commits, and PR descriptions remain in normal English. Only the explanatory prose around code is compressed, and technical terms like "polymorphism" stay exact.

When should I not use caveman mode?▼

Avoid it for user-facing writing such as commits, PR descriptions, or documentation where full sentences are expected. It is designed for quick technical exchanges where brevity matters more than polish.

Does compressed phrasing lose technical accuracy?▼

No. The rules only remove articles, filler, hedging, and pleasantries. Technical substance, exact terminology, and code remain unchanged, so answers stay correct while using far fewer tokens.

Related Skills

Explore More Software Engineering Skills→
LayerDynamicsLayerDynamics

outline-understanding-user-request

Analyze code files to formulate targeted clarifying questions about scope and integration.

Community
Intermediate
Aitronos-DevelopmentAitronos-Development

test-fix

Diagnose failing tests, apply formatting and linting fixes, and re-run the test suite.

Official
Advanced
mscipiomscipio

token-tracker

Monitor AI model context window usage and warn before token overflow.

Community
Advanced
generic-automation-and-itgeneric-automation-and-it

ai-mansplain

Reformats a single reply into terse bullet-and-table output ending with a TL;DR block.

Official
Basic