Verified:GitHub

caveman

Compress assistant responses into caveman-style prose while preserving technical accuracy.

199|41|Updated Oct 25, 2020

Search Tags:#technical writing #token efficiency #response compression #classical Chinese #chat style #debugging assistance #mode persistence

Ready to run

npx skills add https://github.com/rvdbreemen/OTGW-firmware --skill caveman-rvdbreemen

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/rvdbreemen/OTGW-firmware/tree/main/.agents/skills/caveman
Command: npx skills add https://github.com/rvdbreemen/OTGW-firmware --skill caveman-rvdbreemen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Users need shorter, lower-token responses without losing technical correctness, especially during fast back-and-forth troubleshooting.

Core Features & Use Cases

Ultra-compressed response style: Converts answers into caveman-style prose by dropping filler, hedging, and many articles while keeping full technical substance.
Intensity levels for control: Supports lite, full (default), ultra, and multiple Wenyan classical compression modes.
Session persistence with safety exceptions: Stays active across turns, automatically switches back to normal prose for security warnings, irreversible confirmations, and ambiguity-prone multi-step sequences.

Quick Start

Say: enable caveman mode in full intensity and answer my next question in compressed caveman prose.

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 chat responses without losing technical accuracy?▼

Response compression shortens technical writing by dropping filler words and articles into caveman-style prose, reducing tokens while keeping code blocks, symbols, and exact error strings intact.

Can I control the intensity of token compression during debugging assistance?▼

You can control token compression intensity using lite, full, ultra, and wenyan classical Chinese variants, which adjusts how aggressively response verbosity is reduced during interactive Q&A.

Does response compression mode persist across multiple turns in a chat session?▼

Session persistence keeps caveman compression active across multiple chat turns, maintaining your selected intensity level until you explicitly disable it or trigger a safety exception.

When should I not use compressed caveman mode for technical writing?▼

Caveman compression automatically disables itself for security warnings, destructive confirmations, and ambiguity-prone multi-step sequences, ensuring critical details remain fully verbose and clear.

What is the best way to enable caveman mode for brief technical troubleshooting responses?▼

To enable caveman mode, instruct the chat to enable caveman mode in full intensity and answer your next question in compressed caveman prose.