tiktok-research by bradautomates/head-of-content
npx skills add https://github.com/bradautomates/head-of-content --skill tiktok-research研究高表现的 TikTok 视频,识别异常值,并分析热门视频内容的钩子和结构。
APIFY_TOKEN 环境变量或在 .env 文件中GEMINI_API_KEY 环境变量或在 .env 文件中apify-client 和 google-genai Python 包.claude/context/tiktok-accounts.md 中配置的账户验证设置:
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"
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
RUN_FOLDER="tiktok-research/$(date +%Y-%m-%d_%H%M%S)" && mkdir -p "$RUN_FOLDER" && echo "$RUN_FOLDER"
python3 .claude/skills/tiktok-research/scripts/fetch_tiktok.py \
--days 30 \
--limit 50 \
--sorting latest \
--output {RUN_FOLDER}/raw.json
参数:
--days: 回溯搜索的天数(默认:30)--limit: 每个账户的最大视频数(默认:50)--sorting: "latest"、"popular" 或 "oldest"(默认:latest)--usernames: 使用特定用户名覆盖账户文件python3 .claude/skills/tiktok-research/scripts/analyze_posts.py \
--input {RUN_FOLDER}/raw.json \
--output {RUN_FOLDER}/outliers.json \
--threshold 2.0
输出 JSON 包含:
total_videos: 分析的视频数量outlier_count: 发现的异常值数量topics: 热门话题标签、声音和关键词accounts: 分析的账户列表outliers: 包含互动指标的异常值视频数组python3 .claude/skills/video-content-analyzer/scripts/analyze_videos.py \
--input {RUN_FOLDER}/outliers.json \
--output {RUN_FOLDER}/video-analysis.json \
--platform tiktok \
--max-videos 5
从每个视频中提取:
有关完整的输出模式以及钩子/格式类型,请参阅 video-content-analyzer 技能。
读取 {RUN_FOLDER}/outliers.json 和 {RUN_FOLDER}/video-analysis.json,然后生成 {RUN_FOLDER}/report.md。
报告结构:
# TikTok 研究报告
生成时间:{date}
## 表现最佳的钩子
按互动量排序。为你的内容使用这些公式。
### 钩子 1:{technique} - @{username}
- **开场**:"{opening_line}"
- **为何有效**:{attention_grab}
- **可复制公式**:{replicable_formula}
- **互动数据**:{diggCount} 点赞,{commentCount} 评论,{playCount} 观看
- [观看视频]({webVideoUrl})
[为每个分析的视频重复此部分]
## 内容结构模式
| 视频 | 格式 | 节奏 | 关键留存技巧 |
|-------|--------|--------|--------------------------|
| @username | {format} | {pacing} | {techniques} |
## 行动号召策略
| 视频 | 行动号召类型 | 行动号召文本 | 放置位置 |
|-------|----------|----------|-----------|
| @username | {type} | "{cta_text}" | {placement} |
## 所有异常值
| 排名 | 用户名 | 点赞 | 评论 | 分享 | 观看 | 互动率 |
|------|----------|-------|----------|--------|-------|-----------------|
[列出所有带有指标和链接的异常值]
## 热门话题
### 热门话题标签
[来自 outliers.json 的 topics.hashtags]
### 热门声音
[来自 outliers.json 的 topics.sounds]
### 热门关键词
[来自 outliers.json 的 topics.keywords]
## 可执行的要点
[将模式综合成 4-6 条具体建议]
## 分析的账户
[列出账户]
专注于可执行的见解。"表现最佳的钩子"部分及其可复制公式应突出显示。
完整流程:
RUN_FOLDER="tiktok-research/$(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。
互动分数 : likes + (3 x comments) + (2 x shares) + (2 x saves) + (0.05 x views)
异常值检测 : 互动率 > 平均值 + (阈值 x 标准差) 的视频
互动率 : (分数 / 粉丝数) x 100
diggCount: 点赞/爱心shareCount: 分享playCount: 视频观看次数commentCount: 评论collectCount: 收藏/书签authorFollowers: 创作者的粉丝数musicName: 视频中使用的声音musicOriginal: 声音是否为原创每周安装量
203
仓库
GitHub 星标
30
首次出现
2026年1月28日
安全审计
安装于
opencode178
gemini-cli174
codex168
github-copilot164
cursor163
amp157
Research high-performing TikTok videos, identify outliers, and analyze top video content for hooks and structure.
APIFY_TOKEN environment variable or in .envGEMINI_API_KEY environment variable or in .envapify-client and google-genai Python packages.claude/context/tiktok-accounts.mdVerify setup:
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"
RUN_FOLDER="tiktok-research/$(date +%Y-%m-%d_%H%M%S)" && mkdir -p "$RUN_FOLDER" && echo "$RUN_FOLDER"
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 usernamespython3 .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 analyzedoutlier_count: Number of outliers foundtopics: Top hashtags, sounds, and keywordsaccounts: List of accounts analyzedoutliers: Array of outlier videos with engagement metricspython3 .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:
See the video-content-analyzer skill for full output schema and hook/format types.
Read {RUN_FOLDER}/outliers.json and {RUN_FOLDER}/video-analysis.json, then generate {RUN_FOLDER}/report.md.
Report Structure:
# TikTok Research Report
Generated: {date}
## Top Performing Hooks
Ranked by engagement. Use these formulas for your content.
### Hook 1: {technique} - @{username}
- **Opening**: "{opening_line}"
- **Why it works**: {attention_grab}
- **Replicable Formula**: {replicable_formula}
- **Engagement**: {diggCount} likes, {commentCount} comments, {playCount} views
- [Watch Video]({webVideoUrl})
[Repeat for each analyzed video]
## Content Structure Patterns
| Video | Format | Pacing | Key Retention Techniques |
|-------|--------|--------|--------------------------|
| @username | {format} | {pacing} | {techniques} |
## CTA Strategies
| Video | CTA Type | CTA Text | Placement |
|-------|----------|----------|-----------|
| @username | {type} | "{cta_text}" | {placement} |
## All Outliers
| Rank | Username | Likes | Comments | Shares | Views | Engagement Rate |
|------|----------|-------|----------|--------|-------|-----------------|
[List all outliers with metrics and links]
## Trending Topics
### Top Hashtags
[From outliers.json topics.hashtags]
### Top Sounds
[From outliers.json topics.sounds]
### Top Keywords
[From outliers.json topics.keywords]
## Actionable Takeaways
[Synthesize patterns into 4-6 specific recommendations]
## Accounts Analyzed
[List accounts]
Focus on actionable insights. The "Top Performing Hooks" section with replicable formulas should be prominent.
Full pipeline:
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.
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
diggCount: Likes/heartsshareCount: SharesplayCount: Video viewscommentCount: CommentscollectCount: Saves/bookmarksauthorFollowers: Creator's follower countmusicName: Sound used in videomusicOriginal: Whether sound is originalWeekly Installs
203
Repository
GitHub Stars
30
First Seen
Jan 28, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
opencode178
gemini-cli174
codex168
github-copilot164
cursor163
amp157
Python PDF处理教程:合并拆分、提取文本表格、创建PDF文件
54,200 周安装
Cloudflare Images 图像托管与转换 API 使用指南 | 支持 AI 人脸裁剪与内容凭证
328 周安装
Swift iOS HomeKit Matter 开发指南:控制智能家居与设备配网
329 周安装
iOS WeatherKit 使用指南:获取天气数据、预报与警报的 Swift 实现
329 周安装
Microsoft Agent Framework 开发指南:统一Semantic Kernel与AutoGen的AI智能体框架
329 周安装
Spring缓存单元测试指南:@Cacheable、@CacheEvict、@CachePut测试方法与内存缓存管理器
329 周安装
React Native 升级指南:使用 upgrade-react-native 技能轻松升级项目版本
329 周安装