skills.rest
tiankong0101-byte
tiankong0101-byteCOMMUNITY
Explore all skills by this author →
GitHub

huashu-md-html

Convert documents, web pages, and media into markdown, HTML, or DOCX.

Updated May 17, 2026
Search Tags:#markdown#html#document conversion#pandoc#docx#markitdown
One-click install
npx skills add https://github.com/tiankong0101-byte/skills-registry --skill huashu-md-html-tiankong0101-byte
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: huashu-md-html
Source: https://github.com/tiankong0101-byte/skills-registry/tree/main/skills/huashu-md-html
Command: npx skills add https://github.com/tiankong0101-byte/skills-registry --skill huashu-md-html-tiankong0101-byte

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires markitdown[all], html-to-markdown, trafilatura, markdownify, python-docx, Pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

It removes the friction of converting documents, web pages, and media into clean markdown, then publishing that markdown as polished HTML or publisher-ready DOCX.

Core Features & Use Cases

  • Any-to-Markdown ingestion: Convert PDF, DOCX, PPTX, XLSX, EPUB, images, audio, YouTube, ZIP, and URLs into editable markdown with Microsoft markitdown.
  • Markdown publishing pipeline: Render markdown into refined HTML with Pandoc and four opinionated themes, or reverse published HTML back into markdown for archiving.
  • Publisher-grade DOCX output: Produce Word documents with professional typography, embedded images, cover pages, tables of contents, headers, and footers for editorial review and submission.
  • Use case: Take a whitepaper PDF, extract it to markdown, style it as an article or report HTML page, or convert the same source into a clean DOCX for human editing.

Quick Start

Ask the skill to convert your PDF, web page, or markdown file into clean markdown, a polished HTML theme, or a publisher-ready DOCX, and specify the source file or URL plus the output format you want.

Frequently Asked Questions about huashu-md-html

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

FAQPage Schema
How do I convert a PDF to markdown for editing and publishing?▼

You convert PDF to markdown by ingesting the source with markitdown, which extracts text and structure into editable markdown for downstream HTML or DOCX publishing.

Can I extract content from a YouTube video or audio file into markdown?▼

Yes, the skill extracts audio and YouTube content into markdown because markitdown supports media ingestion, allowing you to convert video or audio sources into editable text.

What is the best way to turn a markdown file into a professional Word document?▼

The best way to turn markdown into a Word document is using pandoc and python-docx to generate a publisher-ready DOCX with professional typography, tables of contents, and embedded images.

Does this tool require pandoc and markitdown to convert HTML back to markdown?▼

Reversing published HTML back into markdown requires html-to-markdown and trafilatura for content extraction, while markitdown and pandoc support the broader format conversion pipeline.

What file formats can I convert to markdown besides standard documents?▼

Besides standard documents, you can convert PPTX, XLSX, EPUB, images, audio, YouTube videos, ZIP archives, and URLs into clean markdown using the any-to-markdown ingestion pipeline.

How do I render markdown into a styled HTML page with themes?▼

You render markdown into styled HTML by using pandoc with four opinionated themes, transforming clean markdown into a polished article or report HTML page for web publishing.

Related Skills

Explore More Content & Communication Skills→
mfmezgermfmezger
5

convert-to-markdown

Convert PDF, DOCX, PPTX, XLSX, HTML, EPUB, and images to Markdown.

Community
Intermediate
lovstudiolovstudio
65

lovstudio:any2docx

Convert Markdown documents to editable DOCX files with cover pages, TOC, and themes.

Official
Advanced
valtterimelkkovaltterimelkko
1

webfetch-skill

Extract clean markdown content from web pages using trafilatura.

Community
Intermediate
GregsGreyCodeGregsGreyCode
6

ocr-and-documents

Extract text from PDFs and scanned documents into Markdown output.

Community
Intermediate