AI Agent Skills

以摄影、天空蓝和鼠尾草绿组织户外学习演示，适合介绍研学项目、活动安排与教育计划。

通过温暖背景、醒目标题和彩色剪纸人物展示工作坊与团队创意，适合协作、归属感及参与主题。

在多个界面展示同一提示词，再剪辑生成结果，适合用真实案例说明 Agent 的使用场景。

将产品界面放入暗色摄影棚中的设备画面，围绕真实界面安排滚动、关键操作与品牌收尾。

围绕一个核心概念，用手绘图示与少量标签组织课程或流程，形成清晰可读的视觉笔记。

借助液滴折射与破裂露出品牌标志，适合简短片头、片尾及品牌转场。

在浏览器中选择角色形状、材质与服装，制作头像，也可作为品牌角色工具的起点。

使用克制入场动画与可调整样式变量构建首屏，按产品需求修改文案、配色和交互状态。

Design a statistically rigorous A/B or multivariate test plan — If/Then/Because hypothesis, control and variant specs, required sample size per variant (absolute vs rela…

Design, plan, and analyze A/B tests with statistical rigor. Use when the user asks about A/B testing, split testing, experiment design, statistical significance, sample…

This skill should be used when the user types /collab-audit or requests AI collaboration diagnosis. Analyzes conversation history, artifacts, and work patterns to genera…

Use when designing or analyzing a controlled experiment — falsifiable hypothesis, sample size from an MDE, reading significance/CI/power, CUPED, or rescuing tests that w…

Compare two versions of an LLM-directed document - an original (teacher) and a candidate (student) - across a transfer set and return a per-case behavioural-equivalence…

Compares A/B variants of a WebAsk survey and checks whether the difference is real or within noise. Use when someone asks which variant performs better or is about to ma…

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experimen…

Generate A/B test variants for affiliate content. Triggers on: "create A/B test", "test my headline", "optimize my CTA", "generate variants", "split test ideas", "improv…