本文へスキップ
TakoAPI
スキル一覧に戻る

youtube-video-analyzer

sdrabent 作

Coding Agents & IDEs
640ダウンロード数はclawskills.shが公開している値です
1スター
0閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

Multimodal YouTube video analysis through both audio (transcript) and visual (frame extraction + image analysis)

説明

このスキルでできること

Analyzes YouTube videos through both transcript extraction and frame-by-frame visual analysis. Synchronizes spoken content with extracted video frames by timestamp, enabling step-by-step guides where on-screen UI elements, code, and diagrams are captured alongside what is said.

Unlike transcript-only YouTube tools, it captures visual content, so information shown on screen but not spoken, such as specific button names, menu paths, or code, is not lost.

使いどころ

  • Building step-by-step guides from software tutorial videos
  • Extracting code shown on screen but not read aloud
  • Documenting exact UI click paths from product demo videos
  • Summarizing long explainer videos with timestamped visual anchors
  • Capturing tool usage and hand positions from physical howto videos

ワークフロー例

入力

User asks: Create a step-by-step guide from this YouTube tutorial: https://youtube.com/watch?v=abc123

エージェント
  1. 1

    Fetches video metadata (title, duration, ID) using yt-dlp

  2. 2

    Extracts timestamped transcript via yt-dlp JSON dump and curl

  3. 3

    Downloads video at 720p and extracts keyframes at adaptive intervals using ffmpeg

  4. 4

    Synchronizes each frame with the corresponding transcript segment by timestamp

  5. 5

    Reads each frame image alongside transcript text to generate a structured step-by-step guide

出力

A markdown step-by-step guide with each action timestamped and annotated with visual descriptions of what appears on screen at that moment

要件

  • ffmpeg
  • yt-dlp

インストール

clawhub install sdrabent/youtube-video-analyzer

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク