One-click install
npx skills add https://github.com/anukkrit149/anukkrit-skills --skill caveman-anukkrit149
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/anukkrit149/anukkrit-skills/tree/main/cloud/skills/caveman
Command: npx skills add https://github.com/anukkrit149/anukkrit-skills --skill caveman-anukkrit149

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Caveman mode reduces token usage and chat verbosity by removing filler, hedging, and pleasantries while preserving full technical correctness.

Core Features & Use Cases

  • Ultra-compact responses that drop articles, filler words, pleasantries, and hedging while keeping meaning intact.
  • Structured terse outputs using short phrasing patterns (e.g., [thing] [action] [reason], then [next step]).
  • Safety-aware clarity override that temporarily relaxes the caveman style for security warnings, irreversible confirmations, and multi-step clarification needs.

Quick Start

Tell the assistant to use caveman mode to answer your question briefly with only technical substance and a clear next step.

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 for technical debugging?

To reduce token usage in AI responses, use a brevity mode that drops filler words, articles, and pleasantries while preserving exact technical terms, code blocks, and structured terse phrasing to maintain debugging accuracy.

What is concise response prompting and how does it handle security warnings?

Concise response prompting compresses outputs to essential technical content using a structured terse pattern, but includes a safety-aware clarity override that temporarily relaxes brevity for security warnings and irreversible actions.

How do I make AI explain architecture with low-token answers?

To get low-token answers for architecture explanations, apply a brevity mode that strips hedging and filler, formatting outputs as short phrasing patterns like [thing] [action] [reason], then [next step].

Does concise response mode drop technical accuracy when cutting tokens?

Concise response mode does not drop technical accuracy; it strictly preserves exact technical terms and code blocks while removing only filler, hedging, and pleasantries to cut tokens.

When should I not use brevity mode for technical writing?

You should not use brevity mode when dealing with multi-step clarification needs, irreversible confirmations, or security warnings, as the safety-aware override temporarily relaxes concise outputs to ensure clarity.