Compress natural language memory notes into caveman format.
npx skills add https://github.com/vvedantb/eva --skill compress-vvedantb
Please help me install this Agent Skill. Skill: compress Source: https://github.com/vvedantb/eva/tree/main/.agents/skills/compress Command: npx skills add https://github.com/vvedantb/eva --skill compress-vvedantb
Compress natural language memory notes into caveman format to reduce input token load while preserving critical substance, code, URLs, and structure. It overwrites the original file with the compressed version and saves a human-readable backup as FILE.original.md.
Run caveman <filepath> to compress memory notes and save the original as <filename>.original.md.
High-intent search queries and answers about installing and using this skill.
To reduce input tokens in CLAUDE.md memory notes, compress them into caveman format. This overwrites the original file with a shortened version while preserving code blocks, URLs, and technical terms.
Caveman format compression is a Claude-based method that condenses natural language memory notes into a terse style. It reduces prompt size while maintaining critical substance, file paths, and commands.
Yes, compressing markdown memory notes keeps a backup of the original file. The tool saves a human-readable copy as FILE.original.md before overwriting the primary file with the compressed version.
To compress markdown todos and preferences, run the caveman script with your filepath. This reduces prompt size for AI tasks by applying Claude-based compression while keeping technical content intact.
When compressing natural language memory files, code blocks, URLs, file paths, commands, and technical terms are preserved. The compression targets verbose natural language while protecting structural and technical content.
Yes, you can use this markdown compression on large memory files without losing structure. The Claude-based compression applies validation to maintain original content structure while reducing input token load.
Bonny94ITACompress natural language memory files into caveman format to reduce input tokens.
galekaCompress agent state files into a compact caveman format.
junechen7414Compress markdown memory files into token-efficient prose with backups.
galeepCompress natural language memory files to reduce Claude token usage.
