# Ad experiment design (/ads-test)

/ads-test is a Claude Code skill in the Ads & Social section. It is maintained by AgriciDaniel and published under the MIT license. Designs or reads out ad A/B tests with a hypothesis, sample size and duration, and returns a plain-language decision.

- Web version: https://skills.sgomez.dev/en/s/ads-test
- Section: [Ads & Social](https://skills.sgomez.dev/en/ads.md)
- Author: AgriciDaniel
- License: MIT
- Source: https://github.com/AgriciDaniel/claude-ads/tree/ac21644933910419529bcf81efb95a9ca71edf81/skills/ads-test
- Updated 10 Sept 2026

## How to ask for it

- `Design an A/B test for two different creatives`
- `What sample size do I need for this test to be significant?`
- `Analyze this experiment's results and tell me what won`

## Install

macOS · Linux:

```
curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash
```

Windows:

```
irm https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.ps1 | iex
```


## Author's description

Design and evaluate paid-ad experiments with hypotheses, randomization units, sample-size and duration assumptions, guardrails, platform experiment tools, analysis, and decision rules. Use for A/B test, split test, experiment design, hypothesis, statistical significance, sample size, test duration, or experiment readout.

- [How we review this](https://skills.sgomez.dev/en/methodology.md)