skills.rest
domattioli
domattioliCOMMUNITY
Explore all skills by this author →
GitHub

compress

Compress natural language memory files into caveman format using Python and Claude CLI or Anthropic API with backups and validation retries.

Updated Aug 23, 2026
Search Tags:#automation#markdown#claude#compression#tokens#caveman-format
One-click install
npx skills add https://github.com/domattioli/DomI --skill compress-domattioli
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: compress
Source: https://github.com/domattioli/DomI/tree/main/plugins/caveman/plugins/caveman/skills/compress
Command: npx skills add https://github.com/domattioli/DomI --skill compress-domattioli

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Compresses natural language memory files (CLAUDE.md, todos, preferences) into caveman format to reduce input token usage. The compressed file overwrites the original and a human-readable backup is saved as FILE.original.md.

Core Features & Use Cases

  • Preserve semantic content while dramatically reducing token counts for memory files.
  • Overwrite originals with a compressed version and automatically retain a backup for safety.
  • Works with CLAUDE.md, TODO notes, preferences, and other memory-like Markdown files to streamline AI workflows.

Quick Start

Run caveman compress on a target Markdown memory file to generate a compressed version and a backup.

Frequently Asked Questions about compress

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

FAQPage Schema
How do I reduce input token usage in Claude memory files?▼

To reduce input token usage in Claude memory files, compress natural language Markdown into caveman format. This preserves semantic content and URLs while shrinking token counts for CLAUDE.md, todos, and preferences.

What is caveman format compression for Markdown?▼

Caveman format compression is a token-saving technique that condenses natural language Markdown memory files. It retains the original substance and URLs but overwrites the file with a compressed version, backing up the original as FILE.original.md.

How do I compress CLAUDE.md files using the Claude CLI?▼

You can compress CLAUDE.md files by running a Python-based workflow that calls Claude via the CLI or Anthropic API. This automated process compresses the text and validates results using an included module with up to two retries.

Does compressing memory files delete the original Markdown content?▼

Compressing memory files does not delete original Markdown content. The compressed version overwrites the target file, but the workflow automatically retains a human-readable backup saved as FILE.original.md for safety.

Do I need the Anthropic API to compress Markdown memory files?▼

You need either the Anthropic API or Claude CLI to compress Markdown memory files. The workflow relies on an Anthropic dependency to process the natural language text and generate the compressed caveman format output.

Related Skills

Explore More Software Engineering Skills→
figulazmifigulazmi

token-monitor-setup

Install and configure the Token Monitor SessionEnd hook for Claude Code.

Community
Intermediate
phucle297phucle297

caveman-compress

Compress markdown and text files into a compact caveman format.

Community
Intermediate
vvedantbvvedantb
99

caveman-compress

Compress Markdown memory files into caveman format with backups.

Community
Advanced
phucle297phucle297

compress

Compress natural language memory files into caveman format with Python scripts.

Community
Intermediate