tiktok-ad-research

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

TikTok Ad Research

TikTok广告研究

Follow shared release-shell rules in:

```
postplus-shared
```
release-shell rules

Use this skill when the user wants paid TikTok ad intelligence, not organic creator or content discovery.

Typical requests:

找 TikTok 上跑得好的广告素材
看某个类目 / 国家 / objective 的 top ads
研究竞品广告怎么做 hook、卖点、CTA
从 Creative Center 数据里提炼 ad brief

Read first:

```
postplus-shared
```
research preferences

${CLAUDE_SKILL_DIR}/references/task-shapes.md

${CLAUDE_SKILL_DIR}/references/input-notes.md

${CLAUDE_SKILL_DIR}/references/normalized-schema.md

遵循

postplus-shared

中的发布shell规则：

```
postplus-shared
```
release-shell规则

当用户需要TikTok付费广告情报，而非原生创作者或内容挖掘时，使用此技能。

典型请求：

找 TikTok 上跑得好的广告素材
看某个类目 / 国家 / objective 的 top ads
研究竞品广告怎么做 hook、卖点、CTA
从 Creative Center 数据里提炼 ad brief

请先阅读：

```
postplus-shared
```
研究偏好

${CLAUDE_SKILL_DIR}/references/task-shapes.md

${CLAUDE_SKILL_DIR}/references/input-notes.md

${CLAUDE_SKILL_DIR}/references/normalized-schema.md

Core Rule

核心规则

Do not treat ad data as if it were organic creator data.

This skill is for:

paid creative benchmarking
hook and offer analysis
objective / region / language comparisons
ad-creative sourcing for briefs

This skill is not for:

creator discovery
community comments research
organic content lane mapping

If the user wants organic content or creator research, route to:

${CLAUDE_SKILL_DIR}/_postplus_shared/20-research/tiktok-research/SKILL.reference.md

请勿将广告数据当作原生创作者数据处理。

本技能适用于：

付费创意基准测试
钩子与优惠方案分析
营销目标/区域/语言对比
为广告简报挖掘创意素材

本技能不适用于：

创作者挖掘
社区评论研究
原生内容赛道梳理

如果用户需要原生内容或创作者研究，请引导至：

${CLAUDE_SKILL_DIR}/_postplus_shared/20-research/tiktok-research/SKILL.reference.md

Preferred Actor

首选执行器

Current default:

```
tiktok-creative-center-top-ads
```

Use this actor when the user wants top-performing Creative Center ads and optional analytics or keyframe metrics.

当前默认：

```
tiktok-creative-center-top-ads
```

当用户需要Creative Center中的顶级广告及可选分析或关键帧指标时，使用此执行器。

Minimal Toolchain

最小工具链

Use these pieces in combination:

scrape:

${CLAUDE_SKILL_DIR}/scripts/collection_actor_run.mjs

normalize:

${CLAUDE_SKILL_DIR}/scripts/normalize_tiktok_ads_dataset.mjs

analyze:

${CLAUDE_SKILL_DIR}/scripts/analyze_tiktok_ads_dataset.mjs

组合使用以下组件：

抓取：

${CLAUDE_SKILL_DIR}/scripts/collection_actor_run.mjs

标准化：

${CLAUDE_SKILL_DIR}/scripts/normalize_tiktok_ads_dataset.mjs

分析：

${CLAUDE_SKILL_DIR}/scripts/analyze_tiktok_ads_dataset.mjs

Release-Shell Execution Contract

发布Shell执行约定

keep actor input JSON, raw datasets, normalized datasets, and analysis caches under
```
<work-folder>/.postplus/tiktok-ads/
```
keep only final user-facing summaries or shortlisted exports outside
```
.postplus/
```
start with a bounded first pass before broader ad pulls
if hosted capability is unavailable, unauthorized, or returns a stable network error, stop immediately instead of switching to ad hoc shell glue

将执行器输入JSON、原始数据集、标准化数据集及分析缓存保存在
```
<work-folder>/.postplus/tiktok-ads/
```
路径下
仅将面向用户的最终摘要或精选导出内容放在
```
.postplus/
```
目录外
在进行大范围广告抓取前，先执行小范围的首轮抓取
如果托管功能不可用、未授权或返回持续网络错误，请立即停止操作，不要切换到临时shell脚本

Recommended Workflow

Example

示例

Run the actor:

bash

node ${CLAUDE_SKILL_DIR}/scripts/collection_actor_run.mjs \
  --collection-key tiktok-ads-top \
  --input ${CLAUDE_SKILL_DIR}/templates/top-ads-sample.json \
  --output <work-folder>/.postplus/tiktok-top-ads-raw.json

Normalize:

bash

node ${CLAUDE_SKILL_DIR}/scripts/normalize_tiktok_ads_dataset.mjs \
  --input <work-folder>/.postplus/tiktok-top-ads-raw.json \
  --actor tiktok-creative-center-top-ads \
  --output <work-folder>/.postplus/tiktok-top-ads-normalized.json

Analyze:

bash

node ${CLAUDE_SKILL_DIR}/scripts/analyze_tiktok_ads_dataset.mjs \
  --input <work-folder>/.postplus/tiktok-top-ads-normalized.json \
  --output <work-folder>/.postplus/tiktok-top-ads-analysis.json

运行执行器：

bash

node ${CLAUDE_SKILL_DIR}/scripts/collection_actor_run.mjs \
  --collection-key tiktok-ads-top \
  --input ${CLAUDE_SKILL_DIR}/templates/top-ads-sample.json \
  --output <work-folder>/.postplus/tiktok-top-ads-raw.json

标准化：

bash

node ${CLAUDE_SKILL_DIR}/scripts/normalize_tiktok_ads_dataset.mjs \
  --input <work-folder>/.postplus/tiktok-top-ads-raw.json \
  --actor tiktok-creative-center-top-ads \
  --output <work-folder>/.postplus/tiktok-top-ads-normalized.json

分析：

bash

node ${CLAUDE_SKILL_DIR}/scripts/analyze_tiktok_ads_dataset.mjs \
  --input <work-folder>/.postplus/tiktok-top-ads-normalized.json \
  --output <work-folder>/.postplus/tiktok-top-ads-analysis.json

Good Output

优质输出

Return:

top brands or advertisers in the sample
dominant objectives
repeated hook language
repeated offer language
repeated regions / geo scope
CTA patterns
duration distribution
top ads by likes or CTR when available
whether the sample is spotlight-curated or filter-driven

Separate:

observed ad facts
likely creative implications
missing evidence

返回内容应包含：

样本中的顶级品牌或广告主
主流营销目标
重复出现的钩子话术
重复出现的优惠话术
重复出现的区域/地理范围
CTA模式
广告时长分布
若有数据，显示按点赞量或CTR排序的顶级广告
样本是精选推荐还是筛选得到的

需区分：

观察到的广告事实
可能的创意启示
缺失的证据

Handoff

转接

Escalate after this skill when needed:

ad video structure or spoken-line breakdown -> a dedicated visual analysis workflow
ad creative review after humans inspect outputs ->
```
skills/40-creative/creative-qa
```
organic TikTok benchmark comparison ->
```
skills/20-research/tiktok-research
```

在必要时，使用本技能后可转接至：

广告视频结构或台词拆解 -> 专用视觉分析流程
人工审核后的广告创意评审 ->
```
skills/40-creative/creative-qa
```
TikTok原生内容基准对比 ->
```
skills/20-research/tiktok-research
```

tiktok-ad-research

Original

Translation

TikTok Ad Research

TikTok广告研究

Core Rule

核心规则

Preferred Actor

首选执行器

Minimal Toolchain

最小工具链

Release-Shell Execution Contract

发布Shell执行约定

Recommended Workflow

推荐工作流程

Example

示例

Good Output

优质输出

Handoff

转接