skills.rest
ttphats
ttphatsCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

caveman

Compresses AI responses into terse fragments while preserving technical accuracy.

Updated Jan 28, 2026
Search Tags:#communication style#token efficiency#brevity#wenyan#response compression#prompt mode
One-click install
npx skills add https://github.com/ttphats/project-detedxs26 --skill caveman-ttphats
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/ttphats/project-detedxs26/tree/main/.augment/skills/caveman
Command: npx skills add https://github.com/ttphats/project-detedxs26 --skill caveman-ttphats

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, pleasantries, and hedging while keeping all technical substance intact. ## Core Features & Use Cases - Six intensity levels: lite, full (default), ultra, plus three classical Chinese (wenyan) variants for maximum character reduction. - Persistent mode: Stays active across the entire session until explicitly disabled with "stop caveman" or "normal mode". - Auto-clarity fallback: Automatically reverts to full sentences for security warnings, irreversible actions, and multi-step instructions where fragments could cause misreading. - Use Case: During a long debugging session, say "caveman mode" and receive answers like "Bug in auth middleware. Token expiry check use < not <=." instead of paragraph-length explanations. ## Quick Start Tell the assistant to use caveman mode for the rest of this conversation to get shorter 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?▼

Activate caveman mode by saying "caveman mode", "be brief", or "less tokens". The assistant then drops articles, filler words, and pleasantries while keeping all technical details, cutting token usage by roughly 75%.

How do I turn off caveman mode once it is active?▼

Say "stop caveman" or "normal mode" to revert to standard responses. The mode persists across the entire conversation and never auto-disables, even after many turns.

What intensity levels does caveman mode support?▼

Six levels: lite (tight but full sentences), full (default, drops articles), ultra (abbreviations and arrows), and three wenyan variants using classical Chinese for maximum character compression. Switch with /caveman lite, full, or ultra.

Does caveman mode affect code blocks and error messages?▼

No. Code, comments, commit messages, error messages, and stack traces remain fully formatted and verbatim. Only conversational prose is compressed; technical accuracy is never sacrificed.

When does caveman mode stop being appropriate?▼

It automatically pauses for security warnings, irreversible action confirmations, and multi-step sequences where fragments risk misreading. Full clarity resumes for those parts, then compression continues afterward.

Related Skills

Explore More Content & Communication Skills→
AveerAveer
1

zeus-agents

Create and configure specialized AI agents with YAML frontmatter in OpenCode environments.

Community
Intermediate
tomlupotomlupo

context-management

Manage token budgets in long conversations with search-before-read and progressive disclosure.

Community
Basic
0xharryriddle0xharryriddle
3

context-compression

Generate probes and score context compression quality against a rubric.

Community
Advanced
allankltsnallankltsn

agno-basic-agents

Create Agno agents with personas, streaming, sampling parameters, and context injection.

Community
Basic