genshijin-compress

Official

Compress memory files to cut input tokens.

AuthorInterfaceX-co-jp
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill reduces input token usage by converting natural-language memory files into a compressed “genshijin/original person” style while preserving technical accuracy and structure.

Core Features & Use Cases

  • Token-saving compression for Markdown: Targets natural-language files such as CLAUDE.md, todos, and settings to shrink conversational overhead.
  • Deterministic safety boundaries: Refuses likely secret/credential files and avoids changing code blocks, inline code, URLs, headings, and file paths.
  • Backup + validation + recovery: Writes compressed output over the original after creating FILE.original.md, then validates preservation of headings, code blocks, URLs, and paths; on failures, it performs pin-point fixes without re-compressing fully.

Quick Start

Send the request to your AI: /genshijin-compress <filepath> to compress the specified memory Markdown file in place and save a human-readable backup.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: genshijin-compress
Download link: https://github.com/InterfaceX-co-jp/genshijin/archive/main.zip#genshijin-compress

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.