A/B Test Setup
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.
概览
The A/B Test Setup skill, part of the TerminalSkills/skills repository, provides structured assistance for users looking to design and implement controlled experiments. This tool supports various methodologies, including split testing, multivariate testing, and hypothesis formulation. It is specifically designed to help users create variant copy and test changes across different platforms. While this skill focuses on the planning and design phases of experimentation, it directs users to specific analytics tracking skills for implementation monitoring. Compatible with agents like Claude and Gemini, this resource is maintained within a repository that has earned 71 stars. It serves as a technical guide for marketing and data-driven design tasks, ensuring that experiments are grounded in clear objectives and measurable variants before deployment.
使用场景
安装说明
# Review source first
open https://github.com/TerminalSkills/skills/blob/main/skills/ab-test-setup/SKILL.mdCopy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.
安全提示
Users should ensure that any data or code generated for experiments complies with their local privacy regulations and organizational security policies. As this skill focuses on the design and setup of tests, users are responsible for the secure implementation of tracking scripts and the protection of any sensitive user data collected during the experimentation process.
相关 Skills
Skill Creator
anthropics/skills
创建新技能、修改和改进现有技能,并衡量技能性能。适用于用户希望从零开始创建技能、编辑或优化现有技能、运行评估以测试技能、通过方差分析对技能性能进行基准测试,或优化技能描述以提高触发准确性的场景。
Claude API
anthropics/skills
Claude API / Anthropic SDK 参考指南 — 包含模型 ID、定价、参数、流式传输、工具使用、MCP、智能体、缓存、Token 计数、模型迁移。 TRIGGER — 阅读 BEFORE 并打开目标文件;不要因为其“看起来像单行代码”而跳过 — 适用场景:提示词以任何形式提及 Claude/Anthropic(Claude、Anthropic、Fable、Opus、Sonnet、Haiku、`anthropic`、`@anthropic-ai`、`claude-*`、`us.anthropic.*`、`[1m]`);用户询问关于 LLM(定价/模型选择/限制/缓存) — 绝不回答
MCP Builder
anthropics/skills
创建高质量 MCP (Model Context Protocol) 服务器的指南,使 LLM 能够通过设计良好的工具与外部服务进行交互。在构建 MCP 服务器以集成外部 API 或服务时使用,无论是使用 Python (FastMCP) 还是 Node/TypeScript (MCP SDK)。
CI Cd And Automation
addyosmani/agent-skills
自动化 CI/CD 流水线设置。适用于设置或修改构建和部署流水线。当需要自动化质量门禁、在 CI 中配置测试运行器或建立部署策略时使用。
API And Interface Design
addyosmani/agent-skills
指导稳定的 API 和接口设计。在设计 API、模块边界或任何公共接口时使用。在创建 REST 或 GraphQL 端点、定义模块间的类型契约或建立前后端边界时使用。
Browser Testing With Devtools
addyosmani/agent-skills
通过 Chrome DevTools MCP 在真实浏览器中进行测试。在构建或调试任何在浏览器中运行的内容时使用。当你需要检查 DOM、捕获控制台错误、分析网络请求、分析性能或使用真实运行时数据验证视觉输出时使用。需要配置 chrome-devtools MCP 服务器。