document-conversion

Name: document-conversion
Availability: InStock
Author: nima

Convert HTML documents into structured Markdown or PDF files.

25|3|Updated Jul 14, 2026

Search Tags:#markdown #html #pandoc #conversion #scraping #document

Ready to run

npx skills add https://github.com/nimadorostkar/Claude-Skills-collection --skill document-conversion-nimadorostkar

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: document-conversion
Source: https://github.com/nimadorostkar/Claude-Skills-collection/tree/main/skills/documents/document-conversion
Command: npx skills add https://github.com/nimadorostkar/Claude-Skills-collection --skill document-conversion-nimadorostkar

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires trafilatura, markdownify, playwright.

What problem does it solve?

This skill solves the common issue of data loss during file format conversion, where critical structural elements like tables, headings, and code blocks are stripped away by naive conversion tools.

Core Features & Use Cases

Intelligent Extraction: Uses advanced libraries to strip web navigation and clutter while retaining core content.
Format Versatility: Handles conversions between HTML, Markdown, Office formats, and PDF.
Use Case: Convert a complex technical web article into a clean, structured Markdown file for documentation or generate a professional PDF from HTML that respects modern CSS layouts.

Quick Start

Use the document-conversion skill to transform the provided HTML file into a clean Markdown document while ensuring all tables are preserved.

Frequently Asked Questions about document-conversion

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

FAQPage Schema

How do I convert complex HTML to Markdown without losing tables and code blocks?▼

Converting HTML to Markdown while preserving tables and code blocks requires intelligent extraction libraries that retain structural elements. This skill uses advanced parsing to strip web clutter while maintaining original content hierarchy and data integrity during document normalization.

What is the best way to scrape web articles and normalize them into structured Markdown?▼

Scraping web articles and normalizing them into structured Markdown is best handled by combining content extraction with format conversion. This skill uses trafilatura to strip navigation and markdownify to transform remaining core content into a clean Markdown document.

Does this document conversion approach handle modern CSS layouts when generating PDF files?▼

Yes, this document conversion approach handles modern CSS layouts when generating PDF files. It applies CSS print media emulation alongside Playwright to ensure professional PDF output respects the original layout and structural styling.

Can I use Playwright to convert dynamic web pages into PDF documents?▼

Yes, you can use Playwright to convert dynamic web pages into PDF documents. The skill leverages Playwright to render JavaScript-driven content and applies CSS print media emulation to generate professional PDFs that maintain original structure.

Why does my HTML to Markdown conversion drop headings and tables from the original document?▼

HTML to Markdown conversion drops headings and tables when using naive tools that strip structural elements. This skill solves the data loss problem by using specialized parsing libraries to maintain original content hierarchy and data integrity.

What are the limitations of using trafilatura for web scraping and document normalization?▼

Limitations of using trafilatura for web scraping include its focus on extracting core text content, which may strip complex interactive elements. This skill mitigates this by combining it with Playwright to handle dynamic rendering and complex HTML structures.