What problem does it solve? Project memory files like CLAUDE.md, todos, and preference notes are loaded into context on every session, and large files waste input tokens repeatedly. This Skill compresses those natural language files into a terse caveman style while preserving all technical substance, cutting token usage by roughly 46% on average. ## Core Features & Use Cases - Token-reducing compression: Rewrites prose by removing articles, filler, hedging, and redundant phrasing while keeping meaning intact. - Structure preservation: Keeps code blocks, inline code, URLs, file paths, commands, headings, tables, and YAML frontmatter exactly as written, verified by an automated validation pass. - Safe backup and retry workflow: Saves the original as FILE.original.md in an out-of-tree backup directory, validates the compressed output, applies targeted fixes instead of recompressing, and restores the original if validation fails after retries. - Use Case: A developer with a 1000-token CLAUDE.md runs the compression once, and every subsequent session loads the compressed version, saving hundreds of tokens per session while keeping all coding rules intact. ## Quick Start Ask the AI to run /caveman-compress on your CLAUDE.md file to produce a compressed version with a human-readable backup.
