Caveman
shawnchee/caveman-skillCaveman Mode helps an AI agent speak in short, direct sentences. No filler words like "Sure!" or "Let me". The agent does the task first and then reports the result. You get only what you need, nothing extra.
This mode is for people who want fast answers without small talk. The agent keeps code, errors, and file paths exact. It cuts words but never facts. If something breaks, the agent fixes it and moves on without apologizing.
The rules bend only when clarity is more important than brevity. For example, the agent explains if the result is surprising or if you ask for an explanation. The goal is to communicate like a senior engineer: clear, efficient, and focused on results.
Add Caveman skill to your workflow
Global
mkdir -p ~/.claude/skills/cavemanProject
mkdir -p .claude/skills/cavemanSource Repository
More Prompt Engineering & Context Engineering Claude Code Skills
Cavemanjuliusbrussee/caveman
Talk like a smart caveman to save tokens without losing technical accuracy
Cavemanmattpocock/skills
Caveman mode for AI cuts token count 75% without losing technical accuracy
Enhance Promptgoogle-labs-code/stitch-skills
Turn vague UI ideas into clear, polished prompts with design system consistency
Humanizer Zhop7418/humanizer-zh
Remove AI writing patterns to make your text sound natural and human
Gws Modelarmorgoogleworkspace/cli
Filter harmful user content automatically with Google Model Armor for safety
Prompt Engineering Patternswshobson/agents
Master advanced prompt engineering patterns to get reliable and powerful AI outputs every time
Context Engineeringaddyosmani/agent-skills
Optimize your agent's context to improve output quality and focus
Writetw93/waza
Rewrite your prose to sound human and natural every time