Compress markdown memory files into token-efficient prose with backups.
npx skills add https://github.com/junechen7414/SpringBoot --skill compress-junechen7414
Please help me install this Agent Skill. Skill: compress Source: https://github.com/junechen7414/SpringBoot/tree/main/.agents/skills/compress Command: npx skills add https://github.com/junechen7414/SpringBoot --skill compress-junechen7414
This Skill compresses natural-language memory files like CLAUDE.md, todos, and preferences so they consume fewer tokens every session while preserving the original meaning and structure.
Ask the assistant to compress your memory file at the specified path so it can create a smaller version and save a backup automatically.
High-intent search queries and answers about installing and using this skill.
To reduce tokens in CLAUDE.md memory files, compress natural-language project memory into compact caveman-style prose. This rewriting process shrinks file size while preserving technical content, lowering context overhead for repeated session loading.
Markdown compression preserves code blocks, inline code, URLs, file paths, headings, and tables exactly intact. It validates output and applies retry-based repair to ensure structural and technical content remains safe and accurate.
The best way to compress project memory files for AI context loading is to rewrite prose-heavy markdown into a token-efficient format while automatically saving a .original.md backup. This ensures faster future sessions without losing original meaning or structure.
Compress todo lists and preference documents without losing structure by applying validation rules to headings, code blocks, and paths. The process creates a backup and uses targeted retry repair to keep the compressed file accurate.
You can use anthropic-based tools to shrink markdown files for repeated context. The compression mechanism targets prose-heavy text files used for repeated context loading, rewriting them into a compact format while keeping a backup of the original file.
Memory file compression can break code blocks and URLs if validation fails. This compression skill addresses that by applying validation specifically to headings, code blocks, URLs, and file paths, using retry-based repair to fix broken output safely.
junechen7414Compress prose-heavy markdown memory files into a compact caveman format.
NihaalManafCompress natural language memory files into caveman format with backups.
cwinvestmentsMonitor Headroom proxy health and report compression statistics for Claude Code sessions.
GDSDNSplits large markdown documents into files by level 2 headings.
