compress

Compress natural language memory files into caveman format with backups.

Updated Apr 23, 2026
One-click install
npx skills add https://github.com/fableindigo-gif/animated-system --skill compress-fableindigo-gif
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: compress
Source: https://github.com/fableindigo-gif/animated-system/tree/main/omnianalytix-mirror/.agents/skills/compress
Command: npx skills add https://github.com/fableindigo-gif/animated-system --skill compress-fableindigo-gif

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to reduce input tokens, while preserving all technical substance, code, URLs, and structure.

Core Features & Use Cases

  • Overwrites the original file with a compressed version for token savings
  • Saves a human-readable backup as <filename>.original.md for safety
  • Detects and blocks sensitive files, preserving data privacy
  • CLI-driven workflow with deterministic processing, validation, and retries

Quick Start

Run caveman compress on a memory file to produce 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 tokens in CLAUDE.md memory files?

The compress tool overwrites the original memory file with a compressed version and automatically saves a human-readable backup as <filename>.original.md. This ensures your natural language preferences and todos remain accessible before token reduction.

Does the compress tool work with sensitive files?

Automatic type detection blocks sensitive files to preserve data privacy before compression begins. This prevents accidental overwriting of confidential markdown content while processing standard memory files.

What happens if token compression fails on a memory file?

If token compression fails, the CLI workflow includes automatic token validation and up to two retries to ensure deterministic processing. This error handling prevents corrupted memory files while attempting to produce a valid compressed version.

Can I compress markdown preferences and todos from the command line?

Yes, you can compress markdown preferences and todos using CLI invocation or the /caveman:compress trigger. The command line workflow processes natural language memory files deterministically to save input tokens without losing technical structure.