Compresses model responses into terse caveman-style prose while preserving technical accuracy.
npx skills add https://github.com/taylorelley/skills --skill caveman-taylorelley
Please help me install this Agent Skill. Skill: caveman Source: https://github.com/taylorelley/skills/tree/main/skills/communication/caveman Command: npx skills add https://github.com/taylorelley/skills --skill caveman-taylorelley
useMemo.", saving context window budget for actual code. ## Quick Start Ask the assistant to talk like caveman or invoke /caveman to enable compressed responses for the rest of the session.High-intent search queries and answers about installing and using this skill.
Enable caveman mode by saying "talk like caveman" or invoking /caveman. It strips articles, filler, and pleasantries from every response, cutting output tokens by roughly 65-75% while keeping code and error strings exact.
Say "stop caveman" or "normal mode" to revert to standard prose. The mode otherwise persists for the entire session and does not drift back on its own.
Yes, it preserves the user's dominant language and compresses style rather than translating. It also offers three Classical Chinese (文言文) levels achieving up to 80-90% character reduction.
It automatically drops to normal prose for security warnings, irreversible-action confirmations, ambiguous multi-step sequences, and repeated questions. Compression resumes after the clarity-critical part is done.
No. Code blocks, function names, API names, CLI commands, and exact error strings are always kept verbatim. Only prose is compressed; technical content stays exact at every intensity level.
matsumuratkCompresses Japanese AI responses into terse keyword-style output to reduce token usage.
barkleesandersCompress, mask, cache, and partition context to manage AI agent context limits.
copilot-ldConstruct token-budgeted memory windows from conversation history and tools.
JNRCHAYANCompresses assistant responses into terse, technically accurate language.