skills.rest
yashtekavade
yashtekavadeCOMMUNITY
Explore all skills by this author →
GitHub

caveman

Compress assistant replies into terse, technically accurate text.

Updated Aug 23, 2026
Search Tags:#troubleshooting#technical writing#token optimization#brevity#prompting style#compression modes
One-click install
npx skills add https://github.com/yashtekavade/fast-invoice-generator- --skill caveman-yashtekavade
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/yashtekavade/fast-invoice-generator-/tree/main/.agents/skills/caveman
Command: npx skills add https://github.com/yashtekavade/fast-invoice-generator- --skill caveman-yashtekavade

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The caveman skill reduces token usage and reply verbosity while preserving technical correctness, especially when fast, high-density communication is needed.

Core Features & Use Cases

Ultra-compressed communication: Drops filler, pleasantries, articles, and hedging to produce terse, technically accurate responses.
Intensity modes: Supports multiple compression levels (lite, full, ultra, wenyan-lite, wenyan-full, wenyan-ultra) to match how aggressive the brevity should be.
Safety-aware resumption behavior: Avoids caveman style during security warnings, irreversible confirmations, and multi-step clarification moments, then resumes afterward.

Quick Start

Turn on caveman mode at the brevity you want by telling the assistant: set caveman mode to ultra.

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 responses without losing technical accuracy?▼

To reduce token usage without losing technical accuracy, use a compression mode that strips filler, pleasantries, and hedging while preserving exact technical terms and code blocks. This yields high-density, terse replies ideal for development support and troubleshooting.

What is the best way to get brief technical writing for code troubleshooting?▼

The best way to get brief technical writing for troubleshooting is to apply a brevity compression mode that drops unnecessary language and articles. This produces terse, technically accurate explanations and clearer patterns for steps and warnings.

Can I control how aggressive the token optimization is in my prompt responses?▼

Yes, you can control the aggressiveness of token optimization by setting a specific compression mode. Available intensity levels include lite, full, ultra, and specialized wenyan variants, allowing you to match the exact brevity required for your task.

Does the brevity compression mode affect security warnings or irreversible confirmations?▼

No, the brevity compression mode automatically avoids ultra-short styles during security warnings, irreversible confirmations, and multi-step clarifications. It safely resumes the compressed output style only after the critical interaction is resolved.

Will stripping filler language modify my code blocks during prompt compression?▼

No, stripping filler language does not modify code blocks during prompt compression. The process preserves code blocks unchanged while removing unnecessary language around them, ensuring technical correctness remains intact alongside the optimized output.

Related Skills

Explore More Content & Communication Skills→
DevMHOneDevMHOne

omni-context-rtk

Configure RTK compression settings and filters via REST endpoints.

Community
Advanced
mattbutlerengineeringmattbutlerengineering
1

caveman

Compress technical communication by removing filler while preserving accuracy and code blocks exactly.

Community
Basic
mmartinsolivmmartinsoliv

caveman

Compress AI responses into terse caveman-style language while preserving technical accuracy.

Community
Basic
achmfachmf

caveman-help

Display reference card for Lite, Full Ultra and Wenyan modes and utility commands.

Community
Basic