juliusbrussee

AI memory files grow large and waste input tokens. This skill compresses natural language prose to caveman format, saving 65-75% of tokens while preserving all code, URLs, and technical content.

Code review feedback is often verbose and repetitive, burying actionable items in polite filler. This skill formats each review finding as a single line with exact location, problem, and fix.

AI coding agents produce verbose responses that increase token costs. This quick-reference card lists all caveman mode triggers, skills, and configuration in one view so you can compress agent output by 65-75 percent.

Large memory files like CLAUDE.md waste tokens on every AI session start. This skill compresses them by about 46 percent while keeping all technical content intact.

Developers spend too much time writing verbose commit messages. This skill generates terse, professional Conventional Commits in under 50 characters while preserving the reasoning behind each change.

AI assistants often produce verbose responses that waste tokens and increase costs. Caveman mode cuts output tokens by 65 to 75 percent while preserving full technical accuracy and code quality.