skills.rest
achyutkneupane
achyutkneupaneCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

caveman

Compresses AI responses into terse fragments to reduce token usage while preserving technical accuracy.

Updated Nov 29, 2025
Search Tags:#token efficiency#brevity#response formatting#classical chinese#text compression#prompt style
One-click install
npx skills add https://github.com/achyutkneupane/Blog-Kit --skill caveman-achyutkneupane
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/achyutkneupane/Blog-Kit/tree/main/.ai/skills/caveman
Command: npx skills add https://github.com/achyutkneupane/Blog-Kit --skill caveman-achyutkneupane

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long, filler-heavy AI responses waste tokens and slow down reading. This Skill cuts token usage by roughly 75% by stripping articles, filler words, and pleasantries while keeping all technical substance intact. ## Core Features & Use Cases - Six Intensity Levels: Choose from lite, full (default), ultra, wenyan-lite, wenyan-full, and wenyan-ultra to control compression aggressiveness, including classical Chinese (文言文) modes. - Persistent Mode: Stays active across every response in a session until explicitly disabled with "stop caveman" or "normal mode". - Auto-Clarity Safety: Automatically drops the terse style for security warnings, irreversible action confirmations, and multi-step sequences where fragments could be misread. - Use Case: During a long debugging session, enable ultra mode so every explanation like "Inline obj prop → new ref → re-render. useMemo." costs minimal tokens while code blocks and error messages remain exact. ## Quick Start Tell the AI "use caveman mode" or invoke /caveman to start receiving ultra-compressed responses immediately.

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 chat responses?▼

Enable caveman mode by saying "caveman mode", "be brief", or invoking /caveman. The AI then drops articles, filler words, and pleasantries, cutting token usage by roughly 75% while keeping technical content and code blocks exact.

What intensity levels does caveman mode support?▼

Six levels are available: lite, full (default), ultra, wenyan-lite, wenyan-full, and wenyan-ultra. Switch levels with /caveman lite, /caveman full, or /caveman ultra. The wenyan variants compress responses into classical Chinese.

Does caveman mode stay active across multiple messages?▼

Yes, the mode persists for every response in the session once activated. It only turns off when you say "stop caveman" or "normal mode", and the chosen intensity level persists until changed or the session ends.

When does caveman mode stop being terse automatically?▼

It automatically reverts to clear prose for security warnings, irreversible action confirmations like deleting database tables, multi-step sequences where fragments risk misreading, and when you ask for clarification. Terse style resumes afterward.

Does caveman mode change code blocks or error messages?▼

No, code blocks remain unchanged and errors are quoted exactly. Only the surrounding prose is compressed; technical terms stay precise, and commits or pull requests are still written in normal language.

Related Skills

Explore More Content & Communication Skills→
JNRCHAYANJNRCHAYAN

caveman

Compresses assistant responses into terse, technically accurate language.

Community
Intermediate
RamonsDkaRamonsDka
1

writing-clearly-and-concisely

Apply Strunk's rules to enforce active voice and concise prose.

Community
Intermediate
guanyangguanyang
947

context-compression

Compress conversational data in AI agent sessions to optimize token usage.

Community
Advanced
modu-aimodu-ai
267

speech-video

Generate animated talking head videos from text using Higgsfield's speech-to-video technology.

Official
Intermediate