video-content-analyzer by bradautomates/head-of-content
npx skills add https://github.com/bradautomates/head-of-content --skill video-content-analyzer使用 Gemini AI 分析短视频,提取钩子、内容结构、表达风格和 CTA 策略。
GEMINI_API_KEY 环境变量google-genai 和 requests Python 包python3 .claude/skills/video-content-analyzer/scripts/analyze_videos.py \
--input outliers.json \
--output video-analysis.json \
--platform instagram \
--max-videos 5
| 参数 | 描述 |
|---|---|
--input, -i |
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
| 包含异常帖子的输入 JSON 文件(必需) |
--output, -o | 用于存储结果的输出 JSON 文件(必需) |
--platform, -p | 平台:instagram、tiktok 或 youtube(默认:instagram) |
--max-videos, -n | 要分析的最大视频数(默认:5) |
接受来自特定平台研究技能的异常 JSON。处理两种格式:
[{post1}, {post2}, ...]{"outliers": [{post1}, {post2}, ...]}脚本会自动映射平台特定的字段:
| 平台 | 视频 URL 字段 | 标题/描述 | 用户名 |
|---|---|---|---|
videoUrl | caption | ownerUsername | |
| TikTok | videoUrl, video_url, webVideoUrl | text, desc | authorUsername |
| YouTube | videoUrl, url | title | channelTitle |
TikTok 注意:Apify TikTok Scraper 返回的是 webVideoUrl(TikTok 页面 URL),而不是直接视频下载 URL。Gemini 将尝试从此页面 URL 进行分析。
返回包含每个视频分析的 JSON 数组:
[
{
"post_id": "ABC123",
"username": "creator",
"url": "https://...",
"platform": "instagram",
"likes": 50000,
"comments": 1200,
"views": 500000,
"analysis": {
"hook": {
"technique": "pattern-interrupt",
"opening_line": "Stop scrolling if you...",
"attention_grab": "Creates urgency and targets specific audience",
"replicable_formula": "Stop scrolling if you [pain point]"
},
"content_structure": {
"format": "problem-solution",
"sections": [...],
"pacing": "fast",
"retention_techniques": ["pattern interrupts", "text overlays"]
},
"delivery_style": {
"speaking": "direct-to-camera",
"energy": "high-energy",
"text_overlays": true,
"visual_style": "quick cuts with b-roll"
},
"cta_strategy": {
"type": "follow",
"cta_text": "Follow for more tips",
"placement": "end"
},
"why_it_works": "..."
}
}
]
分析器识别以下钩子类型:
pattern-interrupt - 打破预期模式question - 以引人入胜的问题开场bold-claim - 提出令人惊讶的声明story-tease - 暗示引人入胜的叙事visual-shock - 视觉冲击开场curiosity-gap - 制造信息差direct-address - 针对特定受众发言controversial-take - 两极分化的观点relatable-pain - 针对常见痛点transformation-preview - 展示前后对比problem-solution - 提出问题,提供解决方案listicle - 编号提示/项目story - 叙事弧线tutorial - 分步教程before-after - 转变展示day-in-life - 生活方式内容reaction - 对其他内容的回应hot-take - 观点文章tool-demo - 产品/工具展示每周安装量
151
仓库
GitHub 星标
30
首次出现
2026年1月28日
安全审计
安装于
opencode137
gemini-cli134
codex130
cursor129
github-copilot125
kimi-cli117
Analyze short-form videos with Gemini AI to extract hooks, content structure, delivery style, and CTA strategies.
GEMINI_API_KEY environment variablegoogle-genai and requests Python packagespython3 .claude/skills/video-content-analyzer/scripts/analyze_videos.py \
--input outliers.json \
--output video-analysis.json \
--platform instagram \
--max-videos 5
| Arg | Description |
|---|---|
--input, -i | Input JSON file with outlier posts (required) |
--output, -o | Output JSON file for results (required) |
--platform, -p | Platform: instagram, tiktok, or youtube (default: instagram) |
--max-videos, -n | Max videos to analyze (default: 5) |
Accepts outlier JSON from platform-specific research skills. Handles both formats:
[{post1}, {post2}, ...]{"outliers": [{post1}, {post2}, ...]}The script automatically maps platform-specific fields:
| Platform | Video URL Fields | Caption | Username |
|---|---|---|---|
videoUrl | caption | ownerUsername | |
| TikTok | videoUrl, video_url, webVideoUrl | text, desc |
TikTok Note : The Apify TikTok Scraper returns webVideoUrl (the TikTok page URL) rather than a direct video download URL. Gemini will attempt to analyze from this page URL.
Returns JSON array with analysis for each video:
[
{
"post_id": "ABC123",
"username": "creator",
"url": "https://...",
"platform": "instagram",
"likes": 50000,
"comments": 1200,
"views": 500000,
"analysis": {
"hook": {
"technique": "pattern-interrupt",
"opening_line": "Stop scrolling if you...",
"attention_grab": "Creates urgency and targets specific audience",
"replicable_formula": "Stop scrolling if you [pain point]"
},
"content_structure": {
"format": "problem-solution",
"sections": [...],
"pacing": "fast",
"retention_techniques": ["pattern interrupts", "text overlays"]
},
"delivery_style": {
"speaking": "direct-to-camera",
"energy": "high-energy",
"text_overlays": true,
"visual_style": "quick cuts with b-roll"
},
"cta_strategy": {
"type": "follow",
"cta_text": "Follow for more tips",
"placement": "end"
},
"why_it_works": "..."
}
}
]
The analyzer identifies these hook types:
pattern-interrupt - Breaks expected patternsquestion - Opens with engaging questionbold-claim - Makes surprising statementstory-tease - Hints at compelling narrativevisual-shock - Striking visual openingcuriosity-gap - Creates information gapdirect-address - Speaks to specific audiencecontroversial-take - Polarizing opinionrelatable-pain - Targets common struggleproblem-solution - Present problem, offer fixlisticle - Numbered tips/itemsstory - Narrative arctutorial - Step-by-step how-tobefore-after - Transformation revealday-in-life - Lifestyle contentreaction - Response to other contenthot-take - Opinion piecetool-demo - Product/tool showcaseWeekly Installs
151
Repository
GitHub Stars
30
First Seen
Jan 28, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
opencode137
gemini-cli134
codex130
cursor129
github-copilot125
kimi-cli117
AI Elements:基于shadcn/ui的AI原生应用组件库,快速构建对话界面
56,200 周安装
OpenAI Agents SDK:构建文本/语音AI智能体、多智能体工作流与防护栏应用
359 周安装
Expo应用设计指南:使用Expo Router和NativeWind构建跨平台React Native移动应用
359 周安装
Autoresearch:自主实验循环工具,自动化代码优化与性能改进
564 周安装
LangChain4j RAG实现模式:构建文档对话与知识增强AI应用指南
381 周安装
Next.js 智能体技能编写指南:创建、优化与管理 AI 技能文件
432 周安装
OpenClaw 自动更新器技能 - 保持网关持续更新的自动化解决方案
483 周安装
authorUsername |
| YouTube | videoUrl, url | title | channelTitle |
transformation-preview