Caveman - AI原始人说话风格节省75%token

store

项目简介

Caveman 是一个让 AI 用「原始人」风格说话的技能插件。核心理念很简单：why use many token when few do trick。

效果：节省约 75% 的输出 token，同时保持 100% 的技术准确性。

效果对比

模式	内容	Token
Normal	The reason your React component is re-rendering is likely because you're creating a new object reference on each render cycle. When you pass an inline object as a prop, React's shallow comparison sees it as a different object every time, which triggers a re-render. I'd recommend using useMemo to memoize the object.	69
Caveman	New object ref each render. Inline object prop = new ref = re-render. Wrap in useMemo.	19

四种强度级别

级别	说明
Lite	去除填充词，保持语法，专业但简洁
Full	原始人风格，去掉冠词，碎片化表达
Ultra	最大压缩，电报式表达，缩写一切
文言文	中文古典压缩，用文言文表达技术内容

支持平台

Agent	安装命令
Claude Code	claude plugin marketplace add JuliusBrussee/caveman && claude plugin install caveman@caveman
Codex	Clone repo → /plugins → Search Caveman → Install
Gemini CLI	gemini extensions install https://github.com/JuliusBrussee/caveman
Cursor	npx skills add JuliusBrussee/caveman -a cursor
Windsurf	npx skills add JuliusBrussee/caveman -a windsurf
Copilot	npx skills add JuliusBrussee/caveman -a github-copilot
其他	npx skills add JuliusBrussee/caveman

Benchmark 数据

任务	Normal	Caveman	节省
React re-render bug	1180	159	87%
Auth middleware fix	704	121	83%
PostgreSQL pool	2347	380	84%
Git rebase vs merge	702	292	58%
Average	1214	294	65%

特色功能

• caveman-commit：简洁 commit 消息，50 字符内
• caveman-review：一行代码审查，无废话
• caveman-compress：压缩 CLAUDE.md 文件，节省输入 token 约 46%
• caveman-help：快速参考卡片

项目链接

GitHub: https://github.com/JuliusBrussee/caveman

2026年3月论文 Brevity Constraints Reverse Performance Hierarchies in Language Models 发现：限制大模型输出简短回答，在某些基准测试上准确率提升 26 个百分点。简洁不一定等于不准确。

MIT 许可证 - free like mass mammoth on open plain.