Back to Details

tiktok-research

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

TikTok Research

TikTok研究

Research high-performing TikTok videos, identify outliers, and analyze top video content for hooks and structure.
研究表现优异的TikTok视频，识别异常值内容，并分析Top视频的钩子与结构。

Prerequisites

前提条件

  • APIFY_TOKEN
    environment variable or in 
    .env
  • GEMINI_API_KEY
    environment variable or in 
    .env
  • apify-client
    and 
    google-genai
    Python packages
  • Accounts configured in 
    .claude/context/tiktok-accounts.md
Verify setup:
bash
python3 -c "
import os
try:
    from dotenv import load_dotenv
    load_dotenv()
except ImportError:
    pass
from apify_client import ApifyClient
from google import genai
assert os.environ.get('APIFY_TOKEN'), 'APIFY_TOKEN not set'
assert os.environ.get('GEMINI_API_KEY'), 'GEMINI_API_KEY not set'
" && echo "Prerequisites OK"
  • 配置
    APIFY_TOKEN
    环境变量或在
    .env
    文件中设置
  • 配置
    GEMINI_API_KEY
    环境变量或在
    .env
    文件中设置
  • 安装
    apify-client
    和
    google-genai
    Python包
  • 在
    .claude/context/tiktok-accounts.md
    中配置要追踪的账号
验证环境配置：
bash
python3 -c "
import os
try:
    from dotenv import load_dotenv
    load_dotenv()
except ImportError:
    pass
from apify_client import ApifyClient
from google import genai
assert os.environ.get('APIFY_TOKEN'), 'APIFY_TOKEN not set'
assert os.environ.get('GEMINI_API_KEY'), 'GEMINI_API_KEY not set'
" && echo "Prerequisites OK"

Workflow

工作流程

1. Create Run Folder

1. 创建运行文件夹

bash
RUN_FOLDER="tiktok-research/$(date +%Y-%m-%d_%H%M%S)" && mkdir -p "$RUN_FOLDER" && echo "$RUN_FOLDER"
bash
RUN_FOLDER="tiktok-research/$(date +%Y-%m-%d_%H%M%S)" && mkdir -p "$RUN_FOLDER" && echo "$RUN_FOLDER"

2. Fetch Content

2. 获取内容

bash
python3 .claude/skills/tiktok-research/scripts/fetch_tiktok.py \
  --days 30 \
  --limit 50 \
  --sorting latest \
  --output {RUN_FOLDER}/raw.json
Parameters:
  • --days
    : Days back to search (default: 30)
  • --limit
    : Max videos per account (default: 50)
  • --sorting
    : "latest", "popular", or "oldest" (default: latest)
  • --usernames
    : Override accounts file with specific usernames
bash
python3 .claude/skills/tiktok-research/scripts/fetch_tiktok.py \
  --days 30 \
  --limit 50 \
  --sorting latest \
  --output {RUN_FOLDER}/raw.json
参数说明：
  • --days
    ：回溯搜索的天数（默认值：30）
  • --limit
    ：每个账号的最大视频获取量（默认值：50）
  • --sorting
    ：排序方式，可选"latest"（最新）、"popular"（热门）或"oldest"（最早）（默认值：latest）
  • --usernames
    ：覆盖账号配置文件，指定特定账号

3. Identify Outliers

3. 识别异常值内容

bash
python3 .claude/skills/tiktok-research/scripts/analyze_posts.py \
  --input {RUN_FOLDER}/raw.json \
  --output {RUN_FOLDER}/outliers.json \
  --threshold 2.0
Output JSON contains:
  • total_videos
    : Number of videos analyzed
  • outlier_count
    : Number of outliers found
  • topics
    : Top hashtags, sounds, and keywords
  • accounts
    : List of accounts analyzed
  • outliers
    : Array of outlier videos with engagement metrics
bash
python3 .claude/skills/tiktok-research/scripts/analyze_posts.py \
  --input {RUN_FOLDER}/raw.json \
  --output {RUN_FOLDER}/outliers.json \
  --threshold 2.0
输出JSON包含：
  • total_videos
    ：分析的视频总数
  • outlier_count
    ：找到的异常值视频数量
  • topics
    ：热门话题标签、背景音乐和关键词
  • accounts
    ：分析的账号列表
  • outliers
    ：包含参与度指标的异常值视频数组

4. Analyze Top Videos with AI

4. 用AI分析Top视频

bash
python3 .claude/skills/video-content-analyzer/scripts/analyze_videos.py \
  --input {RUN_FOLDER}/outliers.json \
  --output {RUN_FOLDER}/video-analysis.json \
  --platform tiktok \
  --max-videos 5
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}/outliers.json \
  --output {RUN_FOLDER}/video-analysis.json \
  --platform tiktok \
  --max-videos 5
从每个视频中提取：
  • 钩子技巧与可复用公式
  • 内容结构与分段
  • 留存用户的技巧
  • CTA策略
查看
video-content-analyzer
技能获取完整输出 schema 及钩子/格式类型。

5. Generate Report

5. 生成报告

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
，生成
{RUN_FOLDER}/report.md
。
报告结构：
markdown
undefined

TikTok Research Report

TikTok研究报告

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.
按参与度排名。可直接复用这些公式创作内容。

Hook 1: {technique} - @{username}

钩子1：{技巧} - @{账号名}

  • Opening: "{opening_line}"
  • Why it works: {attention_grab}
  • Replicable Formula: {replicable_formula}
  • Engagement: {diggCount} likes, {commentCount} comments, {playCount} views
  • Watch Video
[Repeat for each analyzed video]
  • 开场语："{开场台词}"
  • 生效原因：{抓点说明}
  • 可复用公式：{公式内容}
  • 参与度数据：{diggCount}点赞，{commentCount}评论，{playCount}播放
  • 观看视频
[为每个分析的视频重复上述模块]

Content Structure Patterns

内容结构模式

VideoFormatPacingKey Retention Techniques
@username{format}{pacing}{techniques}
视频账号格式节奏核心留存技巧
@账号名{格式}{节奏}{技巧内容}

CTA Strategies

CTA策略

VideoCTA TypeCTA TextPlacement
@username{type}"{cta_text}"{placement}
视频账号CTA类型CTA文案放置位置
@账号名{类型}"{文案内容}"{位置}

All Outliers

所有异常值视频

RankUsernameLikesCommentsSharesViewsEngagement Rate
[List all outliers with metrics and links]
排名账号名点赞数评论数分享数播放量参与率
[列出所有异常值视频的指标及链接]

Trending Topics

热门话题

Top Hashtags

热门话题标签

[From outliers.json topics.hashtags]
[来自outliers.json的topics.hashtags]

Top Sounds

热门背景音乐

[From outliers.json topics.sounds]
[来自outliers.json的topics.sounds]

Top Keywords

热门关键词

[From outliers.json topics.keywords]
[来自outliers.json的topics.keywords]

Actionable Takeaways

可落地建议

[Synthesize patterns into 4-6 specific recommendations]
[将模式总结为4-6条具体建议]

Accounts Analyzed

分析的账号列表

[List accounts]

Focus on actionable insights. The "Top Performing Hooks" section with replicable formulas should be prominent.
[列出所有分析的账号]

重点突出可落地洞察。包含可复用公式的「高表现钩子Top榜单」部分需放在显眼位置。

Quick Reference

快速参考

Full pipeline:
bash
RUN_FOLDER="tiktok-research/$(date +%Y-%m-%d_%H%M%S)" && mkdir -p "$RUN_FOLDER" && \
python3 .claude/skills/tiktok-research/scripts/fetch_tiktok.py -o "$RUN_FOLDER/raw.json" && \
python3 .claude/skills/tiktok-research/scripts/analyze_posts.py -i "$RUN_FOLDER/raw.json" -o "$RUN_FOLDER/outliers.json" && \
python3 .claude/skills/video-content-analyzer/scripts/analyze_videos.py -i "$RUN_FOLDER/outliers.json" -o "$RUN_FOLDER/video-analysis.json" -p tiktok
Then read both JSON files and generate the report.
完整流程命令：
bash
RUN_FOLDER="tiktok-research/$(date +%Y-%m-%d_%H%M%S)" && mkdir -p "$RUN_FOLDER" && \
python3 .claude/skills/tiktok-research/scripts/fetch_tiktok.py -o "$RUN_FOLDER/raw.json" && \
python3 .claude/skills/tiktok-research/scripts/analyze_posts.py -i "$RUN_FOLDER/raw.json" -o "$RUN_FOLDER/outliers.json" && \
python3 .claude/skills/video-content-analyzer/scripts/analyze_videos.py -i "$RUN_FOLDER/outliers.json" -o "$RUN_FOLDER/video-analysis.json" -p tiktok
然后读取两个JSON文件并生成报告。

Engagement Metrics

参与度指标

Engagement Score: 
likes + (3 x comments) + (2 x shares) + (2 x saves) + (0.05 x views)
Outlier Detection: Videos with engagement rate > mean + (threshold x std_dev)
Engagement Rate: (score / followers) x 100
参与度得分：
点赞数 + (3 × 评论数) + (2 × 分享数) + (2 × 收藏数) + (0.05 × 播放量)
异常值识别规则：参与率 > 平均值 + (阈值 × 标准差)的视频
参与率：(得分 / 粉丝数) × 100

TikTok-Specific Fields

TikTok专属字段

  • diggCount
    : Likes/hearts
  • shareCount
    : Shares
  • playCount
    : Video views
  • commentCount
    : Comments
  • collectCount
    : Saves/bookmarks
  • authorFollowers
    : Creator's follower count
  • musicName
    : Sound used in video
  • musicOriginal
    : Whether sound is original
  • diggCount
    ：点赞数/爱心数
  • shareCount
    ：分享数
  • playCount
    ：视频播放量
  • commentCount
    ：评论数
  • collectCount
    ：收藏数/书签数
  • authorFollowers
    ：创作者的粉丝数
  • musicName
    ：视频使用的背景音乐名称
  • musicOriginal
    ：是否为原创背景音乐