Where are the files saved?

By default, files are saved to a 'url-to-markdown' directory, organized by domain and slug, alongside a rendered HTML snapshot for reference.

What happens if the primary conversion fails?

The skill features a robust fallback system that tries an upgraded Defuddle pipeline first, then a legacy extractor, and finally a hosted API if local capture fails entirely.

How does this handle JavaScript-heavy sites?

It uses Chrome CDP to fully render the page, ensuring that content generated by frameworks like React, Vue, or web components is captured correctly before conversion.

Does it support YouTube transcripts?

Yes, it automatically detects YouTube pages and attempts to extract available captions and transcripts directly into the Markdown body.

Can I use this for pages requiring a login?

Yes, you can use the '--wait' mode which allows you to manually log in or navigate the browser before triggering the final capture.

URL to Markdown Converter

Name: URL to Markdown Converter
Author: 812lcl

by812lcl

0•

ウェブスクレイピングとデータ収集

Converts any webpage into clean, structured Markdown using Chrome CDP for accurate rendering of complex web content and media.

This skill leverages Chrome CDP to render pages fully, including JavaScript and Shadow DOM content, before converting them into clean Markdown. It features advanced handling for YouTube transcripts, automatic fallbacks to secondary conversion pipelines if the primary method fails, and the ability to download images and videos locally for offline use. It is an essential tool for developers and researchers who need to capture web documentation, articles, or video content in a format optimized for LLMs and personal knowledge bases.

主な機能

010 GitHub stars

02Interactive 'Wait Mode' for capturing authenticated or lazy-loaded pages

03Advanced YouTube transcript extraction and content formatting

04Multi-stage conversion pipeline with automatic fallback mechanisms

05Full JavaScript and Shadow DOM rendering via Chrome CDP

06Optional local media downloading for images and videos

ユースケース

01Converting technical documentation into local Markdown files for AI training or offline reference

02Extracting structured content and transcripts from YouTube videos for summaries and analysis

03Archiving blog posts and articles while preserving high-quality formatting and local media

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add 812lcl/dotfiles baoyu-url-to-markdown

For use in Claude.ai and ChatGPT

主な機能

010 GitHub stars

02Interactive 'Wait Mode' for capturing authenticated or lazy-loaded pages

03Advanced YouTube transcript extraction and content formatting

04Multi-stage conversion pipeline with automatic fallback mechanisms

05Full JavaScript and Shadow DOM rendering via Chrome CDP

06Optional local media downloading for images and videos

ユースケース

01Converting technical documentation into local Markdown files for AI training or offline reference

02Extracting structured content and transcripts from YouTube videos for summaries and analysis

03Archiving blog posts and articles while preserving high-quality formatting and local media

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add 812lcl/dotfiles baoyu-url-to-markdown

For use in Claude.ai and ChatGPT