skills.rest
prefactordev
prefactordevOFFICIAL
Explore all skills by this author →
WebsiteGitHub

caveman

Compress technical responses into terse, accurate communication modes.

3|Updated Jan 20, 2026
Search Tags:#prompting#brevity#token-efficiency#caveman#terse#mode-switching
One-click install
npx skills add https://github.com/prefactordev/typescript-sdk --skill caveman-prefactordev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/prefactordev/typescript-sdk/tree/main/.agents/skills/caveman
Command: npx skills add https://github.com/prefactordev/typescript-sdk --skill caveman-prefactordev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ultra-compressed communication mode that reduces token usage while preserving full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Core Features & Use Cases

  • Maintains technical substance with minimal filler and no hedging.
  • Supports dynamic intensity switching via /caveman lite|full|ultra and in-message prompts.
  • Persists across responses with a default mode of full, until explicitly changed or stopped.
  • Supports wenyan-style variants for alternative tonal registers and terseness.

Quick Start

Invoke caveman mode by saying caveman or /caveman and begin receiving terse, technically precise responses.

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 while keeping technical accuracy in AI responses?▼

You can reduce token usage by invoking caveman mode via /caveman or saying 'caveman mode', which strips filler and hedging while maintaining high-signal technical accuracy.

What is the best way to get brief and precise technical summaries from an AI?▼

The best way to get brief, precise technical summaries is to trigger caveman mode, which defaults to full intensity to deliver high-signal technical substance with minimal filler.

Can I adjust the brevity level when using terse prompting modes?▼

Yes, you can adjust brevity by dynamically switching intensity levels using commands like /caveman lite, full, ultra, or wenyan-variants to control the compression and tonal register.

Does the caveman mode persist across multiple chat messages?▼

Yes, caveman mode persists across responses by default until you explicitly toggle cessation by saying 'stop caveman' or 'normal mode' to return to standard communication.

How do I switch back to normal mode after enabling terse communication?▼

To switch back to normal mode, simply say 'stop caveman' or 'normal mode' to toggle cessation and restore standard, full-length conversational output.

Are there different tonal variants available for token-efficient prompting?▼

Yes, token-efficient prompting supports wenyan-style variants including wenyan-lite, wenyan-full, and wenyan-ultra, which provide alternative tonal registers for high-signal communication.

Related Skills

Explore More Software Engineering Skills→
tkerseytkersey
66

seq

Parse Codex JSONL session logs to extract skill usage and token counts.

Community
Basic
gabergergaberger
4

hex-summarize

Generate token-efficient AST summaries of source code using Tree-sitter.

Community
Advanced
MacPhobosMacPhobos

AI Session Compression Techniques

Compress long AI conversations using summarization and embedding-based retrieval.

Community
Advanced
SaltFishGCSaltFishGC

caveman

Compress assistant responses into brief caveman-style prose with adjustable brevity levels.

Community
Intermediate