huashu-md-html skill
A document pipeline skill: anything to markdown, markdown to clean html and publisher-grade docx, and html back to markdown
- 942 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Runs external tools and reads files
- Can fetch web page content by URL
Install
- Works in
Manual install
npx skills add alchaincyf/huashu-md-htmlThen install the dependencies from requirements.txt; docx needs Pandoc.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Runs external tools and reads files
- Can fetch web page content by URL
This is third-party code. Review the repository files before installing.
What it does
The skill combines several document conversions into one pipeline. It turns almost any file (PDF, DOCX, PPTX, XLSX, EPUB, image, audio, a web page URL) into clean markdown, then styles markdown into tidy html with one of its prepared themes or builds a publisher-grade docx from it with a cover, table of contents, embedded images and headers and footers. It also goes the other way: published html can be pulled back into markdown for archiving. Each conversion is a separate command, and the themes passed an anti-AI-slop checklist, so no acid gradients or emoji as icons. Underneath it wires together markitdown, Pandoc, trafilatura and html-to-markdown.
Who it is for. For writers, editors and technical writers who need to move documents between markdown, html and docx.
Good fit when
- You need clean markdown from a PDF, DOCX or web page
- You need to style markdown into tidy html or docx
- You need to pull published html back into markdown
Not a fit when
- You need a single format without conversions
- You cannot install external tools like Pandoc
Example request
Turn this PDF into clean markdown, then style it into html with a calm themeLimitations
The skill relies on external tools (markitdown, Pandoc, trafilatura) that you install from requirements.txt, which needs Python. Extraction quality depends on the source file, and complex layouts or scans may need manual fixes. The themes are fixed; the skill does not draw arbitrary designs.
How to disable. Remove the huashu-md-html skill folder from your agent's skills directory.
FAQ
Which formats convert to markdown?
PDF, DOCX, PPTX, XLSX, EPUB, images, audio and web pages by URL.
Do I need anything besides the skill?
Yes, the external tools from requirements.txt, including Pandoc for docx and conversions.
Discussion
No questions or reviews yet.
Related
SkillsA Firecrawl skill and CLI that lets your agent convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV and PDF to Markdown on your own machine
A skill to convert Markdown to Word and back through Pandoc with ready styling templates and Lua filters
md-to-docx builds a ready Word document from Markdown: tables, footnotes, figure captions, headers and template patching.
A skill that typesets resumes, one-pagers, letters, reports and slides from templates into PDF, PNG and PPTX and checks the result before delivery
A skill and CLI that turn Markdown into DOCX, PDF, PPTX, XLSX, PNG and about a dozen more formats, all computed locally
A CLI and skill that export Feishu and Lark docs, sheets and wikis to Markdown and let an agent read or append to them.
README in short
The README describes the skill as a multi-way document pipeline: anything to markdown, markdown to tidy html or publisher-grade docx, and html back to markdown. Each conversion is a command, and four themes passed an anti-AI-slop check. Underneath it wires markitdown, Pandoc, trafilatura and html-to-markdown. Install is via npx skills add and the skill is agent-agnostic. MIT licensed.