skills.rest
karitham
karithamCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

caveman

Reduce token usage with terse, technically precise responses across conversation turns.

2|Updated Mar 16, 2021
Search Tags:#ai#conversation#brevity#token-efficiency#mode-switch#caveman#intensity
One-click install
npx skills add https://github.com/karitham/dotfiles --skill caveman-karitham
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/karitham/dotfiles/tree/main/modules/opencode/skills/caveman
Command: npx skills add https://github.com/karitham/dotfiles --skill caveman-karitham

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ultra-efficient, high-fidelity communication by reducing token usage without sacrificing technical accuracy.

Core Features & Use Cases

  • Intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra.
  • Activation & persistence: trigger phrases like caveman mode or /caveman and keep the mode across turns until stopped.
  • Clear, concise responses: drop filler, maintain substance, and adapt tone to user preferences.
  • Use Case: ideal for rapid, precise answers in long-running sessions or demos.

Quick Start

Enable caveman mode by saying caveman mode or using /caveman and specify the intensity level if desired.

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 conversations without losing technical accuracy?▼

To reduce token usage in AI conversations, enable a brevity mode that strips filler while maintaining technical precision. This delivers terse responses ideal for debugging, explanations, and quick decisions in long-running sessions.

How do I activate brevity mode and adjust response intensity levels?▼

Activate brevity mode by triggering phrases like caveman mode or using the /caveman command. You can specify intensity levels including lite, full, ultra, or wenyan variants, with full as the default setting.

Does brevity mode persist across multiple turns in ongoing AI conversations?▼

Yes, brevity mode persists across multiple turns in ongoing AI conversations until manually stopped. This ensures consistent token-efficient responses throughout long-running sessions or technical debugging without reactivation.

What's the best way to get concise technical answers for quick debugging decisions?▼

The best way to get concise technical answers for quick debugging decisions is to apply intensity presets like ultra or full. These modes drop conversational filler, adapt tone, and deliver rapid substance-only outputs.

What are the limitations of using high-intensity brevity settings for AI responses?▼

High-intensity brevity settings limit conversational nuance by dropping explanatory context to maximize token efficiency. While technically precise, ultra or wenyan-ultra presets may omit background details needed for complex explanations.

Related Skills

Explore More Content & Communication Skills→
aryaniyapsaryaniyaps
26

caveman

Reduce token usage with terse, technically accurate communication.

Community
Basic
grandinhgrandinh
2

code-review-trigger

Trigger the /code-review command from natural language review requests.

Community
Basic
cody-hutsoncody-hutson

context-budget-auditor

Monitors and reports token consumption for Claude Code sessions, flagging bloated components exceeding thresholds.

Community
Intermediate
Ikram-AlamIkram-Alam

context-optimization

Optimize AI agent context via compaction, masking, KV-cache, and partitioning.

Community
Advanced