caveman-compress

Compress natural language markdown files into caveman format.

13|3|Updated Jun 10, 2026

Search Tags:#markdown #claude #compression #caveman #token saving

Ready to run

npx skills add https://github.com/tassiovale/claude-code-kit --skill caveman-compress-tassiovale

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: caveman-compress
Source: https://github.com/tassiovale/claude-code-kit/tree/main/skills/caveman-compress
Command: npx skills add https://github.com/tassiovale/claude-code-kit --skill caveman-compress-tassiovale

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, and includes scripts (resource) components.

What problem does it solve?

This Skill compresses natural language memory files into caveman format, reducing the number of input tokens Claude needs per session.

Core Features & Use Cases

Memory File Compression: Compresses CLAUDE.md, todos, and preferences into a caveman format to save tokens.
File Backup: Preserves the original file as a human-readable backup.
Use Case: For users with a large CLAUDE.md file, this Skill can reduce the token cost by up to 46% on average, saving thousands of tokens over many sessions.

Quick Start

Compress the CLAUDE.md file using the caveman-compress skill.

Frequently Asked Questions about caveman-compress

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

FAQPage Schema

How do I reduce input tokens for my Claude markdown memory files?▼

You can compress markdown memory files into a caveman format to reduce Claude input tokens. This preserves technical substance, code, URLs, and structure while overwriting the original file and saving a human-readable backup as FILE.original.md.

What is caveman memory compression for markdown files?▼

Caveman memory compression is a technique that condenses natural language markdown into a shortened format. It maintains all technical substance and structural elements while reducing the token count by up to 46% on average for large memory files.

Does compressing memory files preserve my code snippets and URLs?▼

Yes, compressing memory files preserves all technical substance, including code snippets, URLs, and the document structure. The process focuses on condensing natural language text while keeping critical technical details intact.

Will I lose my original markdown file after compression?▼

No, you will not lose your original markdown file. The compression process overwrites the original file with the compressed version but automatically saves a human-readable backup as FILE.original.md.

Do I need Python to run markdown token compression?▼

Yes, you need Python installed to run the markdown token compression scripts. The Skill relies on Python components to execute the caveman compression logic on your memory files.

How do I trigger markdown compression on a specific file?▼

You can trigger markdown compression by using the command /caveman-compress FILEPATH or by prompting "compress memory file". This initiates the script to process your specified markdown document.