content-processor

Fetch YouTube transcripts, web pages, and EPUBs into summaries via Go CLI.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/gh-xj/claude-skills --skill content-processor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: content-processor
Source: https://github.com/gh-xj/claude-skills/tree/main/.claude-plugin/skills/content-processor
Command: npx skills add https://github.com/gh-xj/claude-skills --skill content-processor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandoc, yt-dlp, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the acquisition and summarization of content from multiple sources, turning raw media and documents into concise, actionable insights.

Core Features & Use Cases

  • Unified ingestion: fetch transcripts from YouTube, websites, and EPUBs, then generate consistent summaries.
  • Structured outputs: split books into chapters and produce per-chapter AI summaries, plus overall across formats.
  • Use Case: convert a YouTube lecture and a bookmarked website into organized notes with highlights and a reading-time table.

Quick Start

Use this Skill by running the included CLI commands to process a YouTube video into a transcript, clean the Markdown, and generate a summary. For example: content-processor yt-transcript --url "<youtube-url>" --output-dir ./sources/yt-transcripts content-processor epub-to-md --input "<book.epub>" --output "<book>.md" content-processor md-split --input "<book>-cleaned.md" --level 2

Frequently Asked Questions about content-processor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automatically extract and summarize YouTube transcripts?

You can automatically extract and summarize YouTube transcripts by using a Go-based CLI to fetch the video transcript and generate a concise summary. The workflow fetches the transcript and outputs structured notes into a specified local directory.

What is the best way to convert an EPUB book into structured chapter summaries?

The best way to convert an EPUB into structured chapter summaries is to use a CLI that splits the book into Markdown by heading levels. It processes the EPUB file, cleans the Markdown, and generates per-chapter AI summaries.

Do I need pandoc and yt-dlp installed to process web content and transcripts?

Yes, you need external dependencies like pandoc and yt-dlp installed to process web content and transcripts. These tools enable the CLI to fetch YouTube transcripts and convert web pages into structured Markdown formats.

Can I split a large Markdown file into smaller sections automatically?

Yes, you can split a large Markdown file into smaller sections automatically by running the Markdown split command. This allows you to specify a heading level, breaking the document into manageable chunks for per-section summarization.

Does this content processing approach work for both video lectures and bookmarked web pages?

Yes, this content processing approach works for both video lectures and bookmarked web pages by offering unified ingestion. It fetches transcripts from YouTube and text from websites, turning them into organized notes with highlights and reading-time tables.

Why are my EPUB to Markdown conversions failing to separate chapters correctly?

EPUB to Markdown conversions may fail to separate chapters correctly if the document is not split at the proper heading level. You must specify the correct heading depth in the CLI to ensure the Markdown is partitioned accurately before summarization.