视频内容分析器：AI驱动分析短视频钩子、结构与CTA策略，优化内容创作

video-content-analyzer by bradautomates/head-of-content

275 周安装量

50 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/bradautomates/head-of-content --skill video-content-analyzer

AI/机器学习内容创作数据分析

🇨🇳中文介绍

视频内容分析器

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。

先决条件

GEMINI_API_KEY 环境变量
google-genai 和 requests Python 包

用法

python3 .claude/skills/video-content-analyzer/scripts/analyze_videos.py \
  --input outliers.json \
  --output video-analysis.json \
  --platform instagram \
  --max-videos 5

参数

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

联系我们

相关 Skills

find-skills 技能搜索工具 - Vercel Labs 开源智能体技能包管理器

776,000 周安装

React 组合模式指南：Vercel 组件架构最佳实践，提升代码可维护性

106,200 周安装

Azure Data Explorer (Kusto) 查询技能：KQL数据分析、日志遥测与时间序列处理

102,600 周安装

专业SEO审计工具：全面网站诊断、技术SEO优化与页面分析指南

59,900 周安装

接受来自特定平台研究技能的异常 JSON。处理两种格式：

直接列表：[{post1}, {post2}, ...]
包装格式：{"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
Instagram	`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

🇺🇸English

Video Content Analyzer

Analyze short-form videos with Gemini AI to extract hooks, content structure, delivery style, and CTA strategies.

Prerequisites

GEMINI_API_KEY environment variable
google-genai and requests Python packages

Usage

python3 .claude/skills/video-content-analyzer/scripts/analyze_videos.py \
  --input outliers.json \
  --output video-analysis.json \
  --platform instagram \
  --max-videos 5

Parameters

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)

Input Format

Accepts outlier JSON from platform-specific research skills. Handles both formats:

Direct list: [{post1}, {post2}, ...]
Wrapped: {"outliers": [{post1}, {post2}, ...]}

The script automatically maps platform-specific fields:

Platform	Video URL Fields	Caption	Username
Instagram	`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.

Output

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": "..."
    }
  }
]

Hook Techniques

The analyzer identifies these hook types:

pattern-interrupt - Breaks expected patterns
question - Opens with engaging question
bold-claim - Makes surprising statement
story-tease - Hints at compelling narrative
visual-shock - Striking visual opening
curiosity-gap - Creates information gap
direct-address - Speaks to specific audience
controversial-take - Polarizing opinion
relatable-pain - Targets common struggle
- Shows before/after

Content Formats

problem-solution - Present problem, offer fix
listicle - Numbered tips/items
story - Narrative arc
tutorial - Step-by-step how-to
before-after - Transformation reveal
day-in-life - Lifestyle content
reaction - Response to other content
hot-take - Opinion piece
tool-demo - Product/tool showcase

Weekly Installs

151

Repository

bradautomates/h…-content

GitHub Stars

First Seen

Jan 28, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykWarn

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

transformation-preview