skills.rest
forgefabrik
forgefabrikCOMMUNITY
Explore all skills by this author →
GitHub

caveman

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

Updated Jun 5, 2026
Search Tags:#token efficiency#compression#caveman#session persistence#wenyan#response style#terse writing
One-click install
npx skills add https://github.com/forgefabrik/agent-bigbrother --skill caveman-forgefabrik
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/forgefabrik/agent-bigbrother/tree/main/.agents/skills/caveman
Command: npx skills add https://github.com/forgefabrik/agent-bigbrother --skill caveman-forgefabrik

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns ordinary assistant replies into short, high-density prose so users can save tokens and scan answers faster without losing technical meaning.

Core Features & Use Cases

  • Terse Response Mode: Removes filler, hedging, and pleasantries while keeping facts, code, symbols, and error text exact.
  • Intensity Levels: Lets users choose between lite, full, ultra, and wenyan variants to match the desired compression style.
  • Persistent Session Control: Keeps the mode active across turns until explicitly stopped, making it useful for long debugging sessions or concise drafting workflows.

Quick Start

Ask the assistant to respond in caveman mode for your next answer and keep the technical details exact.

Frequently Asked Questions about caveman

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

FAQPage Schema
How do I compress LLM responses to save tokens without losing technical accuracy?▼

This Skill compresses LLM responses into terse, high-density prose by stripping filler and hedging while preserving exact code, symbols, and error strings to save tokens without losing technical accuracy.

Can I keep concise response mode active across multiple turns for a long debugging session?▼

Yes, you can keep concise response mode active across multiple turns for a long debugging session using persistent session-wide control, which stays on until explicitly switched back to normal prose.

What intensity levels are available for terse writing and response compression?▼

Available intensity levels for terse writing and response compression include lite, full, ultra, and wenyan variants, allowing you to match the desired compression style for token-sensitive interactions.

Does high-density prose compression retain exact code snippets and error strings?▼

Yes, high-density prose compression retains exact code snippets and error strings, automatically applying clarity exceptions to ensure technical details remain precise and undamaged during token reduction.

When should I not use terse writing mode for assistant replies?▼

You should not use terse writing mode when outputs require extensive narrative explanation, conversational hedging, or pleasantries, as the compression mechanism actively strips these elements to maximize density.

Related Skills

Explore More Content & Communication Skills→
phucle297phucle297

caveman

Compress text output into concise caveman-style responses across multiple turns.

Community
Advanced
tyevanstyevans
14

expand

Expand sparse findings into detailed descriptions with cited evidence.

Community
Intermediate
InterfaceX-co-jpInterfaceX-co-jp
304

genshijin-stats

Report real token usage and estimated savings from Claude Code session logs.

Official
Basic
human-avatarhuman-avatar
212

writing-prose-elevation

Audit prose for abstraction, weak verbs, and sensory grounding, then rewrite a sample passage.

Official
Intermediate