caveman-compress

You can compress markdown memory files into a caveman format to reduce Claude input tokens. This preserves technical substance, code, URLs, and structure while overwriting the original file and saving a human-readable backup as FILE.original.md.

Caveman memory compression is a technique that condenses natural language markdown into a shortened format. It maintains all technical substance and structural elements while reducing the token count by up to 46% on average for large memory files.

Yes, compressing memory files preserves all technical substance, including code snippets, URLs, and the document structure. The process focuses on condensing natural language text while keeping critical technical details intact.

No, you will not lose your original markdown file. The compression process overwrites the original file with the compressed version but automatically saves a human-readable backup as FILE.original.md.

Yes, you need Python installed to run the markdown token compression scripts. The Skill relies on Python components to execute the caveman compression logic on your memory files.

You can trigger markdown compression by using the command /caveman-compress FILEPATH or by prompting "compress memory file". This initiates the script to process your specified markdown document.