Verified:GitHub

caveman

Compress assistant responses into terse, token-efficient prose while preserving technical accuracy.

Updated Jul 2, 2025

Search Tags:#technical communication #token efficiency #session persistence #concise writing #response compression #prompt style

Ready to run

npx skills add https://github.com/junechen7414/SpringBoot --skill caveman-junechen7414

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/junechen7414/SpringBoot/tree/main/.bob/skills/caveman
Command: npx skills add https://github.com/junechen7414/SpringBoot --skill caveman-junechen7414

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill compresses responses into terse, high-signal prose so users can reduce token usage without losing technical accuracy.

Core Features & Use Cases

Caveman-style rewriting: Removes filler, hedging, pleasantries, and extra wording while preserving meaning.
Multiple compression levels: Supports lite, full, ultra, and wenyan variants for different terseness needs.
Session persistence: Stays active across turns until explicitly stopped, making it useful for long technical conversations.
Use case: A developer asks for a concise explanation of a React rerender bug and gets a short, precise answer that keeps code and error details intact.

Quick Start

Tell the assistant to use caveman mode and ask for a concise answer about your technical problem.

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 technical conversations without losing code and error details?▼

To reduce token usage without losing technical accuracy, you can compress assistant responses into terse prose. This removes filler and hedging while preserving exact code, symbols, and error strings.

What is the best way to keep AI debugging explanations concise during long-running chats?▼

Keeping AI debugging explanations concise during long-running chats requires a compression mode that stays active across turns. This session persistence ensures ongoing technical conversations maintain shorter outputs without repeatedly enabling the feature.

Can I adjust the terseness level when compressing technical writing for prompt responses?▼

Yes, you can adjust terseness when compressing technical writing by selecting from multiple compression levels. Lite, full, ultra, and wenyan variants support different prompt style needs for response compression.

Does response compression affect the clarity of security warnings and irreversible actions?▼

Response compression does not negatively affect security warnings or irreversible actions. The system automatically applies clarity to ambiguous multi-step instructions, ensuring critical technical details remain clear despite terse prose.

When should I not use terse prose for technical communication?▼

You should avoid terse prose for technical communication when explaining complex architectural concepts to non-technical stakeholders. In these cases, removing filler and hedging may reduce the clarity needed for broad comprehension.