skills.rest
JohannesKonings
JohannesKoningsCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

caveman

Strip filler words from AI responses to reduce token usage by 75%.

1|Updated Aug 1, 2020
Search Tags:#developer workflow#token efficiency#concise output#context optimization#terse communication#technical responses
One-click install
npx skills add https://github.com/JohannesKonings/JohannesKonings.github.io --skill caveman-johanneskonings
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/JohannesKonings/JohannesKonings.github.io/tree/main/.agents/skills/caveman
Command: npx skills add https://github.com/JohannesKonings/JohannesKonings.github.io --skill caveman-johanneskonings

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates excessive token waste and unnecessary fluff in AI technical responses, which bloats context windows and slows down information delivery for users who need fast, direct technical answers.

Core Features & Use Cases

  • 75% Token Reduction: Cuts response token usage by ~75% by stripping articles, filler words, pleasantries, and hedging while retaining 100% technical accuracy.
  • Terse Technical Communication: Delivers direct, fragment-style technical answers ideal for debugging, code reviews, quick troubleshooting, and fast information scanning.
  • Persistent Activation: Stays active across all responses once triggered, only deactivating when the user explicitly requests normal mode or issues a stop caveman command.

Quick Start

Invoke caveman mode by telling the AI "use caveman" or "caveman mode" to receive ultra-terse, token-efficient technical responses for all subsequent queries.

Frequently Asked Questions about caveman

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

FAQPage Schema
How do I reduce AI token usage for technical responses?▼

Reduce AI token usage by stripping filler words, articles, and pleasantries from technical responses. This approach cuts token consumption by approximately 75% while retaining full technical accuracy for debugging and code reviews.

What is the best way to get concise output for code debugging?▼

Concise output for code debugging is achieved by applying ultra-terse communication rules that remove conversational fluff. This delivers direct, fragment-style technical answers ideal for rapid information scanning and troubleshooting.

How do I optimize context window usage during developer workflows?▼

Optimize context window usage by enabling persistent terse communication mode. This prevents context bloat by continuously eliminating non-essential hedging and filler words across all subsequent technical queries.

Does terse communication affect technical accuracy?▼

Terse communication retains 100% technical accuracy. The token reduction mechanism strictly targets non-essential linguistic filler, ensuring precise technical details remain intact for developer workflows.

How do I turn off concise output mode after enabling it?▼

Turn off concise output mode by explicitly requesting normal mode or issuing a stop command. This deactivates the persistent token-reduction behavior and restores standard conversational responses.

Related Skills

Explore More Software Engineering Skills→
vanyastaffvanyastaff
2

ctx-stats

Display token consumption, context savings ratio, and per-tool breakdown for session context-mode usage.

Community
Basic
jinyongpjinyongp
2

caveman

Compress AI responses by removing filler and hedging while preserving technical accuracy.

Community
Basic
Manvendra08Manvendra08
1

token-efficiency

Reduce token consumption and context overflow in LLM interactions.

Community
Basic
gkganesh12gkganesh12
1

gk-cost

Track token usage and dollar costs across AI-assisted development sessions.

Community
Advanced