skills.rest
ahostbr
ahostbrCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ls-caveman-mode

Compress technical responses by removing filler and hedging while preserving code and warnings.

Updated Aug 5, 2026
Search Tags:#technical writing#token efficiency#caveman mode#concise responses#prompting rules#role-based style#low verbosity
One-click install
npx skills add https://github.com/ahostbr/liteharness --skill ls-caveman-mode
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ls-caveman-mode
Source: https://github.com/ahostbr/liteharness/tree/main/liteharness/catalog/skills/ls-caveman-mode
Command: npx skills add https://github.com/ahostbr/liteharness --skill ls-caveman-mode

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

ls-caveman-mode reduces token usage and verbosity by forcing consistently compressed, caveman-style communication without sacrificing technical correctness.

Core Features & Use Cases

  • Token-efficient technical responses: Cuts filler, hedging, and pleasantries while keeping exact technical terminology.
  • Intensity controls: Switch between lite, full, ultra, and wenyan variants to match your desired compression level.
  • Safety-aware brevity: Keeps normal language for warnings and irreversible, confusing, or multi-step sensitive actions, then resumes caveman mode.

Quick Start

Tell your agent: “Use caveman mode ultra to explain how token efficiency improves LLM responses.”

Frequently Asked Questions about ls-caveman-mode

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

FAQPage Schema
How do I reduce token usage in LLM technical responses?▼

Reduce token usage by applying caveman-mode compression to strip filler, hedging, and pleasantries from technical responses while preserving exact terminology and quoted errors. This rule-based approach delivers token-efficient answers without losing technical correctness.

What is caveman mode for concise AI prompting?▼

Caveman mode is a role-based prompting style that enforces ultra-terse, compressed responses for technical conversations. It applies rule-based removal of filler and hedging to maximize token efficiency while keeping exact technical terminology intact.

How do I switch between different levels of low verbosity responses?▼

Switch between intensity variants—lite, full, ultra, and wenyan—to match your desired compression level. Specify the variant in your prompt, such as requesting caveman mode ultra, to control the exact level of response compression applied.

Does caveman mode keep warnings clear for irreversible actions?▼

Caveman mode uses safety-aware brevity, keeping normal language for warnings, irreversible actions, and confusing multi-step sensitive tasks. It resumes compressed caveman-style phrasing only after the critical safety information is fully communicated.

Are code snippets and exact quoted errors preserved in terse responses?▼

Yes, code snippets and exact quoted errors are preserved. The compression rules target filler, hedging, and pleasantries, ensuring that exact technical terminology, code, and specific error messages remain untouched for technical correctness.

Related Skills

Explore More Content & Communication Skills→
achmfachmf

caveman-help

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

Community
Basic
jwiegleyjwiegley
20

caveman

Compress natural language prompts by removing stop words while preserving semantic content.

Community
Basic
docs-plusdocs-plus
88

caveman

Reduce token consumption in AI technical responses by removing filler language.

Official
Intermediate
xg-gh-25xg-gh-25
36

caveman

Reduce AI response verbosity while preserving technical accuracy.

Community
Basic