skills.rest
Bonny94ITA
Bonny94ITACOMMUNITY
Explore all skills by this author →
GitHub

caveman-compress

Compress natural language memory files into caveman format to reduce input tokens.

Updated Jun 21, 2026
Search Tags:#claude#compression#token optimization#memory files#file backup
One-click install
npx skills add https://github.com/Bonny94ITA/BottegaWeb --skill caveman-compress-bonny94ita
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman-compress
Source: https://github.com/Bonny94ITA/BottegaWeb/tree/main/.claude/skills/caveman-compress
Command: npx skills add https://github.com/Bonny94ITA/BottegaWeb --skill caveman-compress-bonny94ita

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Reduces the amount of tokens used when loading memory files into Claude, saving you valuable token usage.

Core Features & Use Cases

  • Memory File Compression: Compresses natural language files (CLAUDE.md, todos, preferences) to save input tokens.
  • File Backup: Preserves the original file with a .original.md extension.
  • Use Case: If you have a large CLAUDE.md file with 1000 tokens, this skill can reduce it to 500 tokens, saving you half the token cost over 100 sessions.

Quick Start

Run /caveman-compress CLAUDE.md to compress the CLAUDE.md file.

Frequently Asked Questions about caveman-compress

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

FAQPage Schema
How do I reduce token usage for my Claude memory files?▼

To reduce Claude memory file token usage, you can compress natural language files like CLAUDE.md into a caveman format. This process halves input tokens, preserving the original file with a .original.md backup extension.

What is the best way to compress a CLAUDE.md file to save input tokens?▼

The best way to compress a CLAUDE.md file to save input tokens is by running a compression command that converts natural language text into caveman format. This can effectively reduce a 1000-token file to 500 tokens over multiple sessions.

Can I compress Claude preference files without losing the original content?▼

Yes, you can compress Claude preference files without losing original content. The compression process automatically creates a backup of the initial natural language file using a .original.md extension before applying token optimization.

Do I need any dependencies to compress Claude todos into caveman format?▼

No, you do not need any dependencies to compress Claude todos into caveman format. The compression skill operates independently without requiring external packages to reduce your input tokens.

How does caveman format compression work for Claude memory files?▼

Caveman format compression works by condensing natural language memory files like CLAUDE.md and todos into a shorthand syntax. This mechanism directly reduces the amount of input tokens loaded into Claude, saving processing costs.

Related Skills

Explore More Software Engineering Skills→
vvedantbvvedantb
99

compress

Compress natural language memory notes into caveman format.

Community
Advanced
fmflurryfmflurry
171

compress

Compress natural language memory files into caveman format with backup.

Community
Advanced
jubalmjubalm
1

claude-code-memory

Manage Claude Code project memory with structured files and Python utilities.

Community
Advanced
VXerysVXerys

caveman-compress

Compress natural language memory files into a compact caveman format.

Community
Intermediate