skills.rest
guhans6
guhans6COMMUNITY
Explore all skills by this author →
GitHub

compress

Compress markdown files into caveman format using the Claude API.

Updated May 11, 2026
Search Tags:#markdown#memory management#file compression#natural language processing#code preservation
One-click install
npx skills add https://github.com/guhans6/agent-workbench --skill compress-guhans6
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: compress
Source: https://github.com/guhans6/agent-workbench/tree/main/platforms/codex/skills/compress
Command: npx skills add https://github.com/guhans6/agent-workbench --skill compress-guhans6

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires scripts.__init__, scripts.__main__, scripts.benchmark, scripts.cli, scripts.compress, scripts.detect, scripts.validate, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill compresses natural language files, such as CLAUDE.md, todos, and preferences, into a caveman format to save input tokens, while preserving all technical substance, code, URLs, and structure.

Core Features & Use Cases

  • Memory File Compression: Compress natural language memory files to reduce input tokens.
  • Technical Preservation: Ensures all technical substance, code, URLs, and structure are preserved.
  • File Overwrite & Backup: Compressed version overwrites the original file, with a human-readable backup saved as FILE.original.md.
  • Trigger Methods: Trigger the compression using the command /caveman:compress <filepath> or by asking the AI to "compress memory file".

Quick Start

Compress the 'memory.md' file using the 'compress' skill.

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 markdown memory files without losing technical content?▼

Compressing markdown files into a caveman format reduces input tokens by stripping verbose natural language while strictly preserving code, URLs, and structural elements. It requires Python 3 and a Claude API key to execute.

Does compressing natural language files overwrite my original markdown documents?▼

Yes, the compressed version overwrites the original markdown file, but a human-readable backup is automatically saved as FILE.original.md to prevent data loss.

What do I need to compress markdown files into a caveman format?▼

You need Python 3 and a Claude API key to compress markdown files into a caveman format. The skill utilizes the Claude API for compression and validation to ensure technical accuracy.

How do I trigger markdown file compression using the Claude API?▼

Trigger markdown file compression by running the `/caveman:compress <filepath>` command or by instructing the AI to compress the memory file. This applies to markdown files containing prose and code.

Is there a way to validate that code and URLs are preserved during token compression?▼

The skill utilizes the Claude API for compression and validation, ensuring all technical substance, code, URLs, and structure are preserved during the markdown file token reduction process.

Related Skills

Explore More Software Engineering Skills→
guhans6guhans6

caveman-compress

Compresses natural language files like CLAUDE.md into a caveman format to reduce tokens for Claude sessions.

Community
Basic
phucle297phucle297

caveman-compress

Compress markdown and text files into a compact caveman format.

Community
Intermediate
qmuqmu
1

translate

Translate English Markdown files while preserving formatting and frontmatter semantics.

Official
Basic
vvedantbvvedantb
99

compress

Compress natural language memory notes into caveman format.

Community
Advanced