Caveman

Translates your modern code requests into caveman speak before processing them, which is exactly as silly as it sounds. You'd use this when you want to add some humor to your workflow or maybe lighten the mood during a late night coding session. The gimmick is straightforward: it rewrites your prompts in broken, primitive language ("me want make function" style) then passes that to Claude. Honestly, it's a novelty that might get a chuckle the first few times, but the practical value tops out pretty quickly unless you're really committed to the bit or showing off conversation style modifications.

skills.sh installs: 509
GitHub stars: 29.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add alirezarezvani/claude-skills --skill caveman --agent claude-code

Installs into .claude/skills of the current project.

Files

Caveman Mode

Derived from Matt Pocock's caveman (MIT). Matt's voice preserved verbatim. Additions: compression tools + references + cs-* wrapper (see references/companion_tooling.md).

Respond terse like smart caveman. All technical substance stay. Only fluff die.

Persistence

ACTIVE EVERY RESPONSE once triggered. No revert after many turns. No filler drift. Still active if unsure. Off only when user says "stop caveman" or "normal mode".

Rules

Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). Abbreviate common terms (DB/auth/config/req/res/fn/impl). Strip conjunctions. Use arrows for causality (X -> Y). One word when one word enough.

Technical terms stay exact. Code blocks unchanged. Errors quoted exact.

Pattern: [thing] [action] [reason]. [next step].

SKILL.md on GitHub