youtube-research

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

YouTube Research

YouTube 内容调研

Research high-performing YouTube outlier videos, analyze top content with AI, and generate actionable reports.

借助工具研究表现优异的YouTube异常视频（outlier videos），利用AI分析优质内容并生成可落地的报告。

Prerequisites

前置条件

```
TUBELAB_API_KEY
```
environment variable. Get key from https://tubelab.net/settings/api
```
GEMINI_API_KEY
```
environment variable (for video analysis)
```
google-genai
```
and
```
requests
```
Python packages

```
TUBELAB_API_KEY
```
环境变量。可从 https://tubelab.net/settings/api 获取密钥
```
GEMINI_API_KEY
```
环境变量（用于视频分析）
```
google-genai
```
和
```
requests
```
Python 包

Workflow

工作流程

Step 1: Create Run Folder

步骤1：创建运行文件夹

bash

mkdir -p youtube-research/$(date +%Y-%m-%d_%H%M%S)

bash

mkdir -p youtube-research/$(date +%Y-%m-%d_%H%M%S)

Step 2: Get Channel ID

步骤2：获取频道ID

Read

.claude/context/youtube-channel.md

to get the channel ID.

读取

.claude/context/youtube-channel.md

文件获取频道ID。

Step 3: Fetch Channel Videos

步骤3：获取频道视频数据

bash

python scripts/get_channel_videos.py CHANNEL_ID --format summary

This returns JSON with the channel's video titles and view counts.

bash

python scripts/get_channel_videos.py CHANNEL_ID --format summary

该命令返回包含频道视频标题和播放量的JSON数据。

Step 4: Analyze Channel

步骤4：分析频道

Analyze the channel data to extract:

keywords: 4 search terms for the channel's direct niche
adjacent-keywords: 4 search terms for topics the same audience watches
audience: 2-3 profiles with objections, transformations, stakes
formulas: Reusable title templates

See

references/channel-analysis-schema.md

for the full schema and example output.

分析频道数据以提取：

keywords：频道核心细分领域的4个搜索关键词
adjacent-keywords：目标受众关注的相邻领域的4个搜索关键词
audience：2-3个受众画像，包含痛点、转化路径、核心诉求
formulas：可复用的标题模板

完整的输出格式和示例可查看

references/channel-analysis-schema.md

。

Step 5: Search for Outliers

步骤5：搜索异常表现视频

Run the outlier search with both keyword sets:

bash

python .claude/skills/youtube-research/scripts/find_outliers.py \
  --keywords "keyword1" "keyword2" "keyword3" "keyword4" \
  --adjacent-keywords "adjacent1" "adjacent2" "adjacent3" "adjacent4" \
  --output-dir youtube-research/{run-folder} \
  --top 5

This runs two searches:

Direct niche: keywords with 5K+ views threshold
Adjacent audience: adjacent-keywords with 10K+ views threshold

Output files:

```
outliers.json
```
- All outliers normalized for video analysis
```
report.md
```
- Basic markdown report
```
thumbnails/*.jpg
```
- Video thumbnails
```
transcripts/*.txt
```
- Video transcripts

使用两组关键词运行异常视频搜索：

bash

python .claude/skills/youtube-research/scripts/find_outliers.py \
  --keywords "keyword1" "keyword2" "keyword3" "keyword4" \
  --adjacent-keywords "adjacent1" "adjacent2" "adjacent3" "adjacent4" \
  --output-dir youtube-research/{run-folder} \
  --top 5

该命令会执行两类搜索：

核心细分领域：使用keywords，播放量阈值为5000+次
相邻受众领域：使用adjacent-keywords，播放量阈值为10000+次

输出文件：

```
outliers.json
```
：所有标准化后的异常视频数据，用于后续分析
```
report.md
```
：基础Markdown报告
```
thumbnails/*.jpg
```
：视频缩略图
```
transcripts/*.txt
```
：视频字幕

Step 6: Filter Relevant Videos for Analysis

步骤6：筛选用于分析的相关视频

Read

outliers.json

and the user's niche from

.claude/context/youtube-channel.md

CRITICAL: Select MAX 3 videos that are most relevant to the user's niche. Filter by:

Title relevance: Title contains keywords related to user's niche/topics
Transcript relevance: If transcript exists, check it mentions relevant topics
Direct niche priority: Prefer videos from direct keyword search over adjacent

Skip videos that are clearly outside the user's content style (e.g., entertainment/vlogs when user does tutorials).

Write the filtered videos to

{RUN_FOLDER}/filtered-outliers.json

json

{
  "outliers": [/* max 3 relevant videos */],
  "filter_reason": "Selected based on relevance to [user's niche]"
}

读取

outliers.json

和

.claude/context/youtube-channel.md

中的用户细分领域信息。

关键要求：最多选择3个与用户细分领域最相关的视频，筛选标准如下：

标题相关性：标题包含与用户细分领域/主题相关的关键词
字幕相关性：若存在字幕，需确认其提及相关主题
核心领域优先级：优先选择核心关键词搜索结果中的视频，而非相邻领域

跳过明显不符合用户内容风格的视频（例如用户做教程类内容，却选择娱乐/vlog类视频）。

将筛选后的视频写入

{RUN_FOLDER}/filtered-outliers.json

：

json

{
  "outliers": [/* 最多3个相关视频 */],
  "filter_reason": "基于与[用户细分领域]的相关性筛选"
}

Step 7: Analyze Top Videos with AI

步骤7：使用AI分析优质视频

bash

python3 .claude/skills/video-content-analyzer/scripts/analyze_videos.py \
  --input {RUN_FOLDER}/filtered-outliers.json \
  --output {RUN_FOLDER}/video-analysis.json \
  --platform youtube \
  --max-videos 3

Extracts from each video:

Hook technique and replicable formula
Content structure and sections
Retention techniques
CTA strategy

See the

video-content-analyzer

skill for full output schema and hook/format types.

bash

python3 .claude/skills/video-content-analyzer/scripts/analyze_videos.py \
  --input {RUN_FOLDER}/filtered-outliers.json \
  --output {RUN_FOLDER}/video-analysis.json \
  --platform youtube \
  --max-videos 3

从每个视频中提取以下信息：

钩子技巧及可复用公式
内容结构与板块划分
留存用户的技巧
CTA策略

完整的输出格式和钩子/内容类型可查看

video-content-analyzer

技能文档。

Step 8: Generate Final Report

步骤8：生成最终报告

Read

{RUN_FOLDER}/outliers.json

and

{RUN_FOLDER}/video-analysis.json

, then generate

{RUN_FOLDER}/report.md

Report Structure:

markdown

undefined

读取

{RUN_FOLDER}/outliers.json

和

{RUN_FOLDER}/video-analysis.json

，然后生成

{RUN_FOLDER}/report.md

。

报告结构：

markdown

undefined

YouTube Research Report

YouTube 内容调研报告

Generated: {date}

生成日期：{date}

Top Performing Hooks

高表现钩子Top榜单

Ranked by engagement. Use these formulas for your content.

按互动量排序。可直接复用这些公式创作内容。

Hook 1: {technique} - {channelTitle}

钩子1：{technique} - {channelTitle}

Video: "{title}"
Opening: "{opening_line}"
Why it works: {attention_grab}
Replicable Formula: {replicable_formula}
Views: {viewCount} | zScore: {zScore}
Watch Video

[Repeat for each analyzed video]

视频："{title}"
开场台词："{opening_line}"
有效原因：{attention_grab}
可复用公式：{replicable_formula}
播放量：{viewCount} | zScore：{zScore}
观看视频

[为每个分析的视频重复上述结构]

Content Structure Patterns

内容结构模式

Video	Format	Pacing	Key Retention Techniques
{title}	{format}	{pacing}	{techniques}

视频	格式	节奏	核心留存技巧
{title}	{format}	{pacing}	{techniques}

CTA Strategies

CTA策略

Video	CTA Type	CTA Text	Placement
{title}	{type}	"{cta_text}"	{placement}

视频	CTA类型	CTA文案	放置位置
{title}	{type}	"{cta_text}"	{placement}

All Outliers

所有异常表现视频

Direct Niche

核心细分领域

Rank	Channel	Title	Views	zScore
[List direct niche outliers]

排名	频道	标题	播放量	zScore
[列出核心领域的异常视频]

Adjacent Audience

相邻受众领域

Rank	Channel	Title	Views	zScore
[List adjacent outliers]

排名	频道	标题	播放量	zScore
[列出相邻领域的异常视频]

Actionable Takeaways

可落地行动建议

[Synthesize patterns into 4-6 specific recommendations based on video analysis]


Focus on actionable insights. The "Top Performing Hooks" section with replicable formulas should be prominent.

[基于视频分析总结4-6条具体的行动建议]


报告需聚焦可落地的洞察，其中包含可复用公式的「高表现钩子Top榜单」部分需突出展示。

Quick Reference

快速参考

Full pipeline:

bash

RUN_FOLDER="youtube-research/$(date +%Y-%m-%d_%H%M%S)" && mkdir -p "$RUN_FOLDER" && \
python .claude/skills/youtube-research/scripts/find_outliers.py \
  --keywords "k1" "k2" "k3" "k4" \
  --adjacent-keywords "a1" "a2" "a3" "a4" \
  --output-dir "$RUN_FOLDER" --top 5

Then filter outliers for niche relevance (max 3), run video analysis, and generate the report.

完整流程命令：

bash

RUN_FOLDER="youtube-research/$(date +%Y-%m-%d_%H%M%S)" && mkdir -p "$RUN_FOLDER" && \
python .claude/skills/youtube-research/scripts/find_outliers.py \
  --keywords "k1" "k2" "k3" "k4" \
  --adjacent-keywords "a1" "a2" "a3" "a4" \
  --output-dir "$RUN_FOLDER" --top 5

之后筛选出与细分领域相关的异常视频（最多3个），运行视频分析，最后生成报告。

Script Reference

脚本参考

get_channel_videos.py

python .claude/skills/youtube-research/scripts/get_channel_videos.py CHANNEL_ID [--format json|summary]

Arg	Description
`CHANNEL_ID`	YouTube channel ID (24 chars)
`--format`	`json` (full data) or `summary` (for analysis)

python .claude/skills/youtube-research/scripts/get_channel_videos.py CHANNEL_ID [--format json|summary]

参数	描述
`CHANNEL_ID`	YouTube频道ID（24位字符）
`--format`	`json` （完整数据）或 `summary` （用于分析）

find_outliers.py

python .claude/skills/youtube-research/scripts/find_outliers.py --keywords K1 K2 K3 K4 --adjacent-keywords A1 A2 A3 A4 --output-dir DIR [options]

Arg	Description
`--keywords`	Direct niche keywords (4 recommended)
`--adjacent-keywords`	Adjacent topic keywords (4 recommended)
`--output-dir`	Output directory (required)
`--top`	Videos per category (default: 5)
`--days`	Days back to search (default: 30)
`--json`	Also save raw JSON data

Output:

outliers.json

report.md

thumbnails/

transcripts/

python .claude/skills/youtube-research/scripts/find_outliers.py --keywords K1 K2 K3 K4 --adjacent-keywords A1 A2 A3 A4 --output-dir DIR [options]

参数	描述
`--keywords`	核心细分领域关键词（推荐4个）
`--adjacent-keywords`	相邻领域关键词（推荐4个）
`--output-dir`	输出目录（必填）
`--top`	每个分类返回的视频数量（默认：5）
`--days`	搜索的时间范围（默认：30天）
`--json`	同时保存原始JSON数据

输出内容：

outliers.json

、

report.md

、

thumbnails/

、

transcripts/

Scoring Algorithm

评分算法

Videos ranked by:

zScore × recency_boost

zScore: How much video outperforms its channel average
recency_boost: 1.0 for today, decays 5%/day (min 0.3×)

视频排名公式：

zScore × recency_boost

zScore：视频表现超出频道平均水平的程度
recency_boost：当日视频为1.0，每日衰减5%（最低0.3倍）