skills.rest
Tyler-R-Kendrick
Tyler-R-KendrickCOMMUNITY
Explore all skills by this author →
GitHub

caveman

Compress model responses into terse prose across six intensity levels.

1|Updated Jul 12, 2026
Search Tags:#optimization#compression#brevity#technical-writing#token-efficiency
One-click install
npx skills add https://github.com/Tyler-R-Kendrick/slm-training --skill caveman-tyler-r-kendrick
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/Tyler-R-Kendrick/slm-training/tree/main/.agents/skills/caveman
Command: npx skills add https://github.com/Tyler-R-Kendrick/slm-training --skill caveman-tyler-r-kendrick

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill addresses excessive token consumption in long-running AI sessions by stripping away conversational filler, pleasantries, and hedging while maintaining full technical accuracy.

Core Features & Use Cases

  • Multi-Level Compression: Offers six intensity levels ranging from professional tight prose to extreme classical Chinese (wenyan) compression.
  • Technical Preservation: Ensures code blocks, error strings, API names, and technical symbols remain untouched and verbatim.
  • Use Case: Use this during complex debugging sessions to reduce output length by 65% without losing the critical technical context required to solve the problem.

Quick Start

Activate the caveman mode by telling the assistant to talk like a caveman or by using the slash command /caveman.

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 without losing technical accuracy?▼

Token efficiency is achieved by compressing model outputs into ultra-terse, high-density prose. This strips conversational filler while preserving code blocks, API names, and technical symbols verbatim, cutting output length by up to 65%.

What is the best way to compress technical writing for long-running AI debugging sessions?▼

Technical writing compression for debugging is handled through six intensity levels, ranging from professional tight prose to extreme classical Chinese. An auto-clarity guardrail ensures technical safety and readability during complex interactions.

Does token compression affect code blocks or error strings in the output?▼

Token compression does not alter code blocks, error strings, or API names. Strict technical preservation rules ensure these critical symbols remain untouched and verbatim to maintain debugging safety.

How do I activate ultra-terse communication for my current session?▼

Ultra-terse communication is activated by telling the assistant to talk like a caveman or by using the slash command. This enforces strict persistence rules to maintain high-density prose throughout the interaction.

Can I use classical Chinese compression for technical documentation?▼

Classical Chinese compression, specifically wenyan, is supported as an extreme intensity level for technical documentation. It minimizes token consumption while retaining core technical accuracy and density.

Related Skills

Explore More Content & Communication Skills→
KyonaxKyonax

session-reset

Compact long-running AI development session context into structured 6-section blocks.

Community
Advanced
forgefabrikforgefabrik

caveman

Compress assistant responses into terse prose while preserving exact code and symbols.

Community
Intermediate
Svenja-devSvenja-dev
38

token-budget-advisor

Estimate token consumption and recommend chunked execution plans for large tasks.

Community
Basic
tzengyuxiotzengyuxio
43

wenyan-xianqin

Rewrite modern Chinese text into terse Pre-Qin prose using a 20-item checklist.

Community
Advanced