Opt-in ultra-compressed OUTPUT style for OMK — port of JuliusBrussee/caveman (MIT, pin 0d95a81). Cuts output tokens ~65% (measured, range 22-87%) by speaking terse while keeping technical terms, code, errors, API names, CLI commands byte-exact. OUTPUT ONLY: 0% input/context/thinking reduction; adds ~1-1.5k input tokens per turn; net loss on terse Q&A or per-request/credit billing (Copilot etc). Six levels: lite / full (default) / ultra / wenyan-lite / wenyan-full / wenyan-ultra; switch via /caveman <level>. Trigger when user says "caveman", "/caveman", "talk like caveman", "brief mode", "less tokens", "be brief", "짧게 답해", "토큰 아껴", "간결하게". Opt-in ONLY (disable-model-invocation): never auto-fires; explicit invocation required. Code/commits/PRs stay normal style. Orthogonal to headroom (headroom = input/context compression; caveman = output prose).
$npx -y skills add dmae97/omk --skill cavemanInstalls into the current project.
Run `npx skills use "https://github.com/dmae97/omk" --skill "dmae97/omk/caveman"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/dmae97/omk" that are relevant to the current task. Run `npx skills add "https://github.com/dmae97/omk"` and select the relevant skills, then follow their instructions.