<p align=“center”> <picture> <source media=“(prefers-color-scheme: dark)” srcset=“assets/logo-dark.png”> </picture> </p>

<p align=“center”> <picture> <source media=“(prefers-color-scheme: dark)” srcset=“assets/logo-dark.png”> </picture> </p>

<h1 align=“center”>Ponytail</h1>

<h1 align=“center”>马尾辫</h1>

<p align=“center”> He says nothing. He writes one line. It works. </p>

<p align=“center”> 他沉默不语。他写下一行代码。然后就能运行。 </p>

<p align=“center”> </p>

<p align=“center”> </p>

<p align=“center”> <a href=“https://trendshift.io/repositories/50668” target=“_blank” rel=“noopener noreferrer”></a> <a href=“https://trendshift.io/repositories/50668” target=“_blank” rel=“noopener noreferrer”></a> </p>

<p align=“center”> <a href=“https://trendshift.io/repositories/50668” target=“_blank” rel=“noopener noreferrer”></a> <a href=“https://trendshift.io/repositories/50668” target=“_blank” rel=“noopener noreferrer”></a> </p>

<p align=“center”> ~54% less code (up to 94%) · ~20% cheaper · ~27% faster · 100% safe

_{Measured on real Claude Code sessions editing a real open-source repo (FastAPI + React), against the same agent with no skill. ~54% is the mean across 12 feature tasks (Haiku 4.5, n=4); it reaches 94% where an agent over-builds (a date picker) and is near zero where the code is already minimal. ponytail keeps every safety guard while a bare “write one-liners” prompt drops one. (The earlier single-shot benchmark reported 80-94% as a flat figure; against a fair agentic baseline that is the per-task ceiling, not the average.) <a href=“benchmarks/results/2026-06-18-agentic.md”>Full writeup</a> · <a href=“benchmarks/“>reproduce it</a>.} </p>

<p align=“center”> 代码减少约54%（最高94%）· 成本降低约20% · 速度提升约27% · 100%安全

_{实测数据来自Claude Code编辑真实开源项目(FastAPI + React)的会话，对比相同但无此技能的代理。54%是12个功能任务的平均值(Haiku 4.5, n=4)；当代理过度构建(如日期选择器)时可达94%，在代码已最简处接近零。ponytail保留所有安全防护，而单纯”写单行代码”的提示会丢失一项。(早期单次基准测试报告的80-94%是统一数值；相对于合理的代理基准线，这是每项任务的上限而非平均值。) <a href=“benchmarks/results/2026-06-18-agentic.md”>完整报告</a> · <a href=“benchmarks/“>复现方法</a>.} </p>

<p align=“center”> _{<a href=“README.es.md”>Español</a> · <a href=“README.ko.md”>한국어</a>} </p>

<p align=“center”> _{<a href=“README.es.md”>西班牙语</a> · <a href=“README.ko.md”>韩语</a>} </p>

<p align=“center”> <a href=“https://ponytail.dev/soon”&gt;</a> </p>

<p align=“center”> <a href=“https://ponytail.dev/soon”&gt;</a> </p>

You know him. Long ponytail. Oval glasses. Has been at the company longer than the version control. You show him fifty lines; he looks at them, says nothing, and replaces them with one.

Ponytail puts him inside your AI agent.

你认识他。留着长马尾。椭圆眼镜。在公司的时间比版本控制系统还久。你给他看五十行代码；他看一眼，一言不发，然后换成一行。

马尾辫把他装进了你的AI代理里。

Before / after

改造前后

You ask for a date picker. Your agent installs flatpickr, writes a wrapper component, adds a stylesheet, and starts a discussion about timezones.

With ponytail:

你要一个日期选择器。你的代理会安装flatpickr、写封装组件、添加样式表，然后开始讨论时区问题。

使用马尾辫后：

 
<input type="date">

 
<input type="date">

More survivors in examples/.

更多幸存案例见examples/。

Numbers

数据

The honest measurement is a real agent doing real work: a headless Claude Code session editing tiangolo’s full-stack-fastapi-template (a real FastAPI + React repo), scored on the git diff it leaves behind. Twelve feature tickets, the same agent with and without the skill, n=4, Haiku 4.5.

真实测量来自实际工作场景：无头Claude Code会话编辑tiangolo的全栈fastapi模板（真实的FastAPI+React仓库），根据留下的git diff评分。12个功能需求单，同一代理启用/禁用该技能，n=4，Haiku 4.5。

<p align=“center”> </p>

<p align=“center”> </p>

🔗 知识库双向关联

• Github__freestylefly_awesome-gpt-image-2_全翻译
• Github__mattpocock_skills_全翻译
• Github__freestylefly_awesome-gpt-image-2_全翻译