Agent Skills 目录

遇到任何 bug、测试失败或意外行为时，在提出修复方案之前使用

实现已完成、所有测试通过、需要决定如何整合成果时使用

展示 ponytail 基准测试的实测收益(代码、成本、速度)。一次性展示。用于 /ponytail-gain、"ponytail 能省什么"、"ponytail 影响"。

对整个代码库做质量审计:bug、安全、真实负载、缺失的测试、性能,以及该删的内容。按重要性排序。

对 diff 做质量审查:bug、安全、真实负载、缺失的测试、性能,以及该删的内容。每条发现都说明会出什么问题、怎么修。

对整个代码库做质量审计:bug、安全漏洞、真实负载下会崩的地方、无测试覆盖的高风险代码、性能瓶颈,以及该删、该合并、该拆分的部分。按优先级排序,每条发现都用大白话解释。只读报告,不改动任何代码。用于 "审计这个代码库"、"review 整个仓库"、"找出冗余"、"哪些能删"、/ponytail-audit。

Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.

Phase 1 示例插件,合成一个 SKILL.md frontmatter,用于向后兼容测试。

从价值、成本和影响三个维度审查 Archify 的 issue、PR 或代码,支持基于证据的维护决策。适用于 issue 分类、变更评审和代码质量评估。

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.

测试关键词分类时使用

帮助用户创建和管理 mirrord 预览环境——在共享的 Kubernetes 集群中以隔离 pod 运行修改后的服务,通过环境密钥和 HTTP/队列流量过滤进行限定,让团队能基于真实流量验证和评审改动,而不影响线上服务。当开发者想临时运行“mirrord preview”、通过链接(mirrord-share-ingress)分享预览,或用 metalbear-co/mirrord-preview GitHub Action 把预览环境接入 CI(如按 PR 生成预览、最小权限集群访问)时使用。

帮助用户在 CI 流水线中配置 mirrord，以针对真实的 Kubernetes 环境做测试。当用户想在 CI 中用 mirrord 连接预发布/共享集群来运行端到端测试、集成测试或自动化测试时使用。

爆款拆解：把一条抖音、小红书、TikTok 或 YouTube 内容拆成开头钩子、带时间的结构节拍、标题公式、封面文字、行动号召和可复用模板。引用的原话逐字核对原文，对不上的删掉并写明删了几条；点赞收藏和话题标签取自平台数据，不由模型编写。用户要拆解爆款、分析对标账号、学习内容结构或准备仿写时使用。通过 LinkDigest API 读取，不需要平台账号或 Cookie。需要 LINKDIGEST_API_KEY；在读取费用上加 1 积分（约 ¥0.14），6 张图以内的图文笔记加拆解共 2 积分。

Use when user wants to create a GitHub issue for the current repository. Must read and follow the repository's issue template format.

Generates Detox E2E tests for React Native apps in JavaScript. Gray-box testing framework with automatic synchronization. Supports local simulators/emulators and TestMu AI cloud. Use when user mentions "Detox", "React Native test", "element(by.id())", "device.launchApp". Triggers on: "Detox", "React Native E2E", "React Native test", "element(by.id)", "device.launchApp".

Generates Cucumber BDD tests with Gherkin feature files and step definitions in Java, JavaScript, or Ruby. Use when user mentions "Cucumber", "Gherkin", "Feature/Scenario", "Given/When/Then", "BDD". Triggers on: "Cucumber", "Gherkin", "BDD", "Feature file", "Given/When/Then", "step definitions".

Generates Codeception tests in PHP covering acceptance, functional, and unit testing. BDD-style with Actor pattern. Use when user mentions "Codeception", "$I->amOnPage", "$I->see", "Cest". Triggers on: "Codeception", "$I->amOnPage", "AcceptanceTester", "Codeception PHP", "Cest".

Generates Behave BDD tests for Python with Gherkin feature files and step implementations. Use when user mentions "Behave", "Python BDD", "Python Gherkin". Triggers on: "Behave", "Python BDD", "behave test", "Python feature file".

Generates Behat BDD tests for PHP with Gherkin feature files and MinkContext for browser testing. Use when user mentions "Behat", "PHP BDD", "Mink", "behat.yml". Triggers on: "Behat", "PHP BDD", "Mink", "behat.yml", "FeatureContext PHP".

Migrate an existing Apple/Swift Expo native module from the Expo Modules API 1.0 definition DSL to the 2.0 macro API (sometimes called v2) while preserving its JavaScript and TypeScript contract. Use when converting or incrementally adopting @ExpoModule, @JS, @Event, @SharedObject, or @Record in an existing module. Do not use for creating a new module, general Expo SDK upgrades, or Android/Kotlin migrations.

Evaluate Expo skills in this repo end-to-end - trigger accuracy, generated code quality, and runtime screenshots on iOS simulator and Android emulator via Expo Go (web optional). Use when the user wants to eval an Expo skill, test that a skill produces working code, benchmark a skill with device screenshots, or verify a skill's output renders correctly.