通过 Skills CLI 安装
使用 npx skills add 将该 skill 安装到选中的 Agent。Phase 0 命令均为按规则生成，尚未验证。
Codex
npx skills add https://github.com/coreyhaines31/marketingskills/blob/main/skills/ad-creative/SKILL.md -g -a codex -y去掉 -g 可改为项目级安装
#1
该品类排名 #1 / 共 94 个· Ranked #1 of 94 in this category
ad creative
ad creative: agent skill — from coreyhaines31/marketingskills.
安装前须知Before you install
✓未声明特殊权限需求No special access needs declared
编辑结论· Editor's verdict
付费广告创意迭代场景下它最合适——变体生成、文案测试、Hook 排序、主流广告平台的格式合规。已经有一版基线广告、想结构化 A/B 多个变体而不丢语调时最强。自然社交内容别用它，转化 vs 互动的权衡完全不同。
Best for paid-ad creative iteration — variant generation, copy testing, hook ranking, format compliance for the major ad platforms. Strongest when you have a baseline ad and want a structured way to A/B test variants without losing voice. Skip it for organic social copy; the conversion-vs-engagement tradeoff is different there.
✓
适合什么场景Best for
- High-star GitHub skill discovery candidate.
✗
不适合什么场景Not for
- Sensitive or production workflows without local review.
vs 其他选择vs alternatives
完整对比表Full compare table →#2aso audit
aso audit: agent skill — from coreyhaines31/marketingskills.
差异 · diffApp Store / Play 商店上架页优化时它最合适——关键词分析、转化率诊断、截图排序、本地化缺口。围绕真实 ASO 工作流构建，不是泛 SEO。大版本发布前或 CVR 平台期最有用。Web SEO 别用它，算法差异够大，这套框架不能直接转嫁。
#3ab-testing
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program.
差异 · diffWhen the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program," or "experiment playbook." Use this whenever someone is comparing two approaches and wants to measure which performs better, or when they want to build a systematic experimentation practice. For tracking implementation, see analytics. For page-level conversion optimization, see cro.
#4ab-test-setup
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program.
差异 · diffWhen the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program," or "experiment playbook." Use this whenever someone is comparing two approaches and wants to measure which performs better, or when they want to build a systematic experimentation practice. For tracking implementation, see analytics-tracking. For page-level conversion optimization, see page-cro.
维度对比side-by-side compare
和同类的关键维度差异| 当前 · this skillad creative | aso audit | ab-testing | ab-test-setup | |
|---|---|---|---|---|
| 评分 · rating | — | — | — | — |
| 星标 · stars | 28k | 28k | 33k | 28k |
| 风险 · risk | 低风险 · low risk | 低风险 · low risk | 中风险 · med risk | 中风险 · med risk |
| 最适合 · best for | High-star GitHub skill discovery candidate. | aso audit: agent skill — from coreyhaines31/marketingskills. | When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. | When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. |
| 不适合 · not for | Sensitive or production workflows without local review. | 需要比当前目录条目更严格人工复核的工作流。 | 需要比当前目录条目更严格人工复核的工作流。 | 需要比当前目录条目更严格人工复核的工作流。 |
审计备注Audit notes
2026-06-10 复查 · last reviewed源码Source公开 GitHub · open on GitHub✓
作者Author社区贡献 · community!
网络访问Network只读 · read-only✓
文件写入Filesystem工作目录沙箱 · sandboxed✓
依赖Dependencies依赖少且通过审计 · audited✓
遥测Telemetry无 · none✓