Agent Skills › AgriciDaniel/claude-ads › ads-test

ads-test

GitHub

用于设计和评估付费广告实验，涵盖假设、随机化单位、样本量计算、持续时间、护栏及决策规则。支持A/B测试、统计显著性分析及实验结果解读。

skills/ads-test/SKILL.md AgriciDaniel/claude-ads

Trigger Scenarios

设计A/B测试或拆分测试方案计算实验所需样本量和持续时间分析实验结果并做出业务决策

Install

npx skills add AgriciDaniel/claude-ads --skill ads-test -g -y

More Options

Use without installing

npx skills use AgriciDaniel/claude-ads@ads-test

指定 Agent (Claude Code)

npx skills add AgriciDaniel/claude-ads --skill ads-test -a claude-code -g -y

安装 repo 全部 skill

npx skills add AgriciDaniel/claude-ads --all -g -y

预览 repo 内 skill

npx skills add AgriciDaniel/claude-ads --list

SKILL.md

Frontmatter

{
    "name": "ads-test",
    "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."
}

Paid Media Experiment

State the decision, causal hypothesis, treatment, control, randomization unit, population, primary metric, guardrails, minimum effect, and stopping rule.
Check platform constraints, overlapping experiments, conversion lag, seasonality, interference, and measurement quality.
Calculate sample and duration from declared assumptions; disclose approximations.
Change one decision surface unless the design explicitly estimates interactions.
Pre-register exclusions, quality checks, analysis, and decision thresholds.
For readout, verify assignment integrity and data completeness before estimating effect and uncertainty.
Return setup or readout in versioned JSON with a plain-language decision.

Do not repeatedly peek and stop on a favorable result, call underpowered noise a winner, or generalize beyond the tested population.