alchaincyf

alchaincyf / huashu-md-html

Public

md/html 双向流水线 · 三个能力一站式：万物→md / md→精美html / html→md。封装 markitdown + Pandoc + html-to-markdown + trafilatura。4 套反 AI slop 主题。Claude Code skill.

92
14
100% credibility
Found May 10, 2026 at 92 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
CSS
AI Summary

A set of tools to convert files like PDFs, documents, images, audio, and URLs into clean Markdown text, render that text into beautifully styled self-contained HTML pages with various themes, or convert existing HTML webpages back to editable Markdown.

How It Works

1
📖 Discover the tool

You find a handy project that turns PDFs, docs, images, videos, or webpages into clean editable text and then into beautiful shareable webpages.

2
🛠️ Set it up quickly

You add the tool to your computer easily so it's ready to use anytime.

3
Pick your starting point
📄
File to webpage

Start with a PDF, presentation, or link and make it into a stunning readable page.

🌐
Webpage to text

Grab content from a website or blog and turn it into clean editable notes.

4
📁 Choose your file or link

Point the tool at your document, image, video, or webpage address.

5
✨ Watch the magic

The tool cleans everything up into simple editable text, removing junk and keeping the good stuff.

6
🎨 Pick a beautiful style

Select from elegant themes like a cozy book, professional report, or easy reading layout.

🎉 Share your creation

Open your new gorgeous webpage that looks like it came from a publisher and share it with anyone.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 92 to 92 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is huashu-md-html?

Huashu-md-html is a md/html bidirectional pipeline on GitHub that handles three core conversions: any file or URL (PDFs, docs, YouTube, web pages) to clean markdown via markitdown; markdown to polished, self-contained HTML with Pandoc and four CSS themes; and HTML back to markdown using html-to-markdown and trafilatura. It solves the pain of juggling formats in AI-assisted workflows, treating markdown as editable source code and HTML as shareable output—no more messy roundtrips losing structure. Install via npx skills add for instant CLI use in tools like Claude Code.

Why is it gaining traction?

It stands out with anti-AI slop themes—crisp, publisher-grade CSS designs without garish gradients or emojis—that produce standalone HTML files ready for blogs or reports. Developers hook on the agent-agnostic skill format and smart URL handling: trafilatura strips noise from articles while preserving metadata from docs. One-command chains like PDF-to-report HTML beat fragmented tools.

Who should use this?

Technical writers archiving blogs or research papers as markdown source. Indie devs turning notes into Medium-style reading pages or interactive docs. AI prompt engineers feeding clean markdown to models, or anyone in Claude/Cursor workflows converting YouTube transcripts to styled HTML.

Verdict

Grab it if you need quick md to html GitHub conversions in agent skills—docs are solid, outputs shine. But with 92 stars and 1.0% credibility score, it's early-stage; test deps like Pandoc first before production.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.