Video Analyzer logo

Video Analyzer

Community
minicoohei
video-analyzer

TikTok/YouTube動画を分析してテンプレート化するスキル。 動画ダウンロード→フレーム抽出→STT→構成分析→テンプレートJSON生成。 競合分析、人気動画の構成学習に使用。 「TikTok分析」「YouTube分析」「動画テンプレート化」「競合動画分析」等で発動。

Overview

Publisherminicoohei
Repositoryai-agent-camp
Skill namevideo-analyzer
Stars
346
Forks
13
Bundled files
4
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by minicoohei on GitHub. Read the source before you install it.

Installation

Install the Video Analyzer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/minicoohei/ai-agent-camp/tree/main/.claude/skills/video-analyzer
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/minicoohei/ai-agent-camp.git /tmp/ai-agent-camp
mkdir -p .claude/skills
cp -r /tmp/ai-agent-camp/.claude/skills/video-analyzer .claude/skills/video-analyzer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Video Analyzer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Video Analyzer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Video Analyzer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Video Analyzer

TikTok/YouTube/Instagram動画をダウンロード→分析→テンプレート化する。

対応プラットフォーム

  • TikTok — https://www.tiktok.com/@user/video/... / https://vt.tiktok.com/...
  • YouTube — https://www.youtube.com/watch?v=... / https://youtu.be/...
  • YouTube Shorts — https://youtube.com/shorts/...
  • Instagram Reels — https://www.instagram.com/reel/...
  • その他 yt-dlp が対応するプラットフォーム

クイックスタート

bash
# TikTok動画を分析
python skills/video-analyzer/scripts/analyze_video.py \
  --url "https://www.tiktok.com/@user/video/123456" \
  --output output/templates/

# YouTube動画を分析
python skills/video-analyzer/scripts/analyze_video.py \
  --url "https://www.youtube.com/watch?v=XXXXX" \
  --output output/templates/

# YouTube Shortsを分析
python skills/video-analyzer/scripts/analyze_video.py \
  --url "https://youtube.com/shorts/XXXXX" \
  --output output/templates/

パイプライン

URL → yt-dlp → 動画ファイル(TikTok/YouTube/Instagram等対応)
  → ffmpeg → フレーム抽出 (1fps)
  → Whisper API → STT (テキスト + タイムスタンプ)
  → Vision AI → フレーム分析 (テロップ位置、デザイン、構図)
  → テンプレート JSON (scenes.json互換)

出力: template.json

json
{
  "source_url": "https://...",
  "duration": 32.5,
  "resolution": "1080x1920",
  "scenes": [
    {
      "frame_number": 1,
      "timestamp": "0:00-0:03",
      "duration": 3.0,
      "narration": "STTから抽出したテキスト",
      "text_overlay": {
        "text": "画面上のテロップ",
        "position": "center",
        "style": "bold",
        "color": "#FFFFFF",
        "has_stroke": true
      },
      "visual": {
        "shot_type": "close_up | medium | wide | overhead",
        "subject": "人物が商品を持っている",
        "transition_to_next": "cut | fade | swipe"
      },
      "motion_type": "i2v",
      "energy": "high | medium | low"
    }
  ],
  "summary": {
    "total_scenes": 8,
    "avg_scene_duration": 4.1,
    "full_transcript": "...",
    "category": "tutorial",
    "caption_style": "太字白テキスト、黒ストローク、画面中央下",
    "structure": "hook → problem → solution → demo → CTA",
    "pacing": "fast | medium | slow",
    "key_techniques": ["technique1", "technique2"]
  }
}

使い方

1. 単体分析

bash
python analyze_video.py --url "URL"

2. バッチ分析(複数URL)

bash
python analyze_video.py --urls-file urls.txt --output output/templates/

3. Playbook蓄積(別スキル)

分析結果のtemplate.jsonを video-playbook スキルに渡して、タイプ別知見を蓄積:

bash
python skills/video-playbook/scripts/manage_playbook.py --add -t output/templates/template.json

4. テンプレートを使って新動画生成

分析結果のtemplate.jsonをstoryboard-generatorに渡して、自社コンテンツでリメイク:

bash
python generate_storyboard.py --template output/templates/template.json --topic "自社プロダクト名"

依存

  • yt-dlp (.bin/yt-dlp)
  • ffmpeg (.bin/ffmpeg)
  • OpenAI Whisper API (STT)
  • Gemini Vision API (フレーム分析)

環境変数

  • OPENAI_API_KEY — Whisper STT用
  • GEMINI_API_KEY — Vision分析用

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Video Analyzer AI skill do?

TikTok/YouTube動画を分析してテンプレート化するスキル。 動画ダウンロード→フレーム抽出→STT→構成分析→テンプレートJSON生成。 競合分析、人気動画の構成学習に使用。 「TikTok分析」「YouTube分析」「動画テンプレート化」「競合動画分析」等で発動。

Why use Video Analyzer on TypingMind?

Because you install it once and use it with any model. Video Analyzer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Video Analyzer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/minicoohei/ai-agent-camp/tree/main/.claude/skills/video-analyzer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Video Analyzer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Video Analyzer?

As many as you like. As long as a model supports skills, you can use Video Analyzer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Video Analyzer AI skill free?

It is published on GitHub by minicoohei. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇