skills.rest
kreuzberg-dev
kreuzberg-devOFFICIAL
Explore all skills by this author →
WebsiteGitHub

Metadata Extraction for html-to-markdown

Extract document metadata, headers, links, images, and structured data during HTML-to-Markdown conversion.

836|66|Updated Feb 3, 2025
Search Tags:#markdown#html#metadata#content analysis#extraction#seo
One-click install
npx skills add https://github.com/kreuzberg-dev/html-to-markdown --skill metadata-extraction-for-html-to-markdown
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Metadata Extraction for html-to-markdown
Source: https://github.com/kreuzberg-dev/html-to-markdown/tree/main/.ai-rulez/skills/metadata-extraction
Command: npx skills add https://github.com/kreuzberg-dev/html-to-markdown --skill metadata-extraction-for-html-to-markdown

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines content analysis by extracting valuable metadata directly during the HTML-to-Markdown conversion process, eliminating the need for separate parsing passes.

Core Features & Use Cases

  • Single-Pass Extraction: Gathers metadata (document info, headers, links, images, structured data) in one traversal.
  • Configurable: Allows selective extraction of metadata types to optimize performance and memory usage.
  • Use Case: Automatically extract all headings, links, and image sources from an HTML article to generate a table of contents, perform SEO analysis, or build an internal link map.

Quick Start

Use the metadata extraction skill to convert the provided HTML content and retrieve all document metadata, headers, and links.

Frequently Asked Questions about Metadata Extraction for html-to-markdown

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

FAQPage Schema
How do I extract metadata from HTML while converting to Markdown?▼

Extract metadata during HTML to Markdown conversion using a single-pass process that gathers document details, headers, links, images, and structured data like JSON-LD simultaneously.

What is the best way to extract structured data like JSON-LD and Microdata from HTML?▼

The best way to extract structured data like JSON-LD is during a single-pass HTML to Markdown conversion, which captures Microdata and RDFa alongside headers and links without requiring separate parsing passes.

Can I extract only specific metadata types like links and images to optimize performance?▼

Yes, you can configure selective metadata extraction to target only specific types like links and images, which optimizes performance and minimizes memory overhead during the HTML conversion process.

Does extracting headers and links during HTML conversion support SEO analysis?▼

Extracting headers and links during HTML conversion directly supports SEO analysis by providing classified links and header hierarchies from the document, enabling tasks like internal link mapping.

How to generate a table of contents from HTML headings?▼

To generate a table of contents from HTML headings, extract headers with their hierarchy levels during the HTML to Markdown conversion, capturing the document structure in a single traversal.

Related Skills

Explore More Software Engineering Skills→
ArcanexisArcanexis
13

fetch

Fetch web pages and convert them into Markdown-formatted text.

Community
Advanced
HwFeeHwFee

ub2-markdown-report-generator

Generate structured Markdown reports with executive summary, methodology, findings, analysis, recommendations, and references.

Community
Intermediate
dhar174dhar174
1

markdown-to-html

Converts Markdown documents to HTML for web display or static sites.

Community
Intermediate
MO196931MO196931

pptx

Create, edit, and analyze PowerPoint .pptx files with OOXML validation.

Community
Advanced