skills.rest
jonaspm
jonaspmCOMMUNITY
Explore all skills by this author →
Website𝕏@jperusmGitHub

caveman

Rewrite assistant responses into terse caveman-style prose with selectable intensity levels.

39|3|Updated Apr 12, 2026
Search Tags:#communication#token efficiency#brevity#caveman#response style#tone control
One-click install
npx skills add https://github.com/jonaspm/bunwright --skill caveman-jonaspm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/jonaspm/bunwright/tree/main/.agents/skills/caveman
Command: npx skills add https://github.com/jonaspm/bunwright --skill caveman-jonaspm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill rewrites responses in a compact caveman style so users can reduce token usage and get faster, denser answers without losing technical meaning.

Core Features & Use Cases

  • Terse response mode: Produces short, fragment-friendly replies that keep the core technical facts intact.
  • Intensity control: Supports lite, full, ultra, and wenyan variants for different compression and tone needs.
  • Persistent behavior: Stays active across turns until the user switches back to normal mode.
  • Use cases: Helpful for debugging, quick explanations, and any workflow where brevity matters more than polish.

Quick Start

Tell the assistant to use caveman mode and answer the next request in the default full intensity.

Frequently Asked Questions about caveman

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

FAQPage Schema
How do I make LLM responses more token-efficient without losing technical accuracy?▼

To make responses token-efficient, you can apply a terse tone control style that compresses outputs into short, fragment-friendly prose while preserving core technical facts. This reduces token usage and provides denser answers.

Can I control the intensity of brief response styles for different workflows?▼

Yes, you can control response brevity using selectable intensity levels. You can choose from lite, full, ultra, and wenyan variants to match different compression and tone needs for troubleshooting or quick explanations.

How does persistent caveman mode work across multiple chat turns?▼

Persistent caveman mode stays active across multiple chat turns, continuously applying terse response compression until explicitly switched back. It only returns to normal mode when you directly request it.

What is the best way to get brief troubleshooting answers for debugging workflows?▼

The best way to get brief troubleshooting answers is to activate a terse response style that prioritizes density over polish. This produces short, fragment-friendly replies that keep the core technical facts intact for debugging.

Does tone control compression affect the technical meaning of the response?▼

Tone control compression does not affect technical meaning. The response style rewrites outputs into compact prose while explicitly preserving technical accuracy, ensuring the core facts remain intact despite the brevity.

Related Skills

Explore More Content & Communication Skills→
sanity-iosanity-io
4

shape-your-agent

Craft system prompts for Sanity Agent Context MCP agents.

Official
Intermediate
tyevanstyevans
14

expand

Expand sparse findings into detailed descriptions with cited evidence.

Community
Intermediate
vrcmsvrcms
1

token-budget-advisor

Estimate token usage and control response depth for AI queries.

Community
Intermediate
dobrinz123dobrinz123

anti-ai

Apply pre-generation anti-AI rules to reduce detection risk in writing.

Community
Basic