Metadata Extraction for html-to-markdown

Official

Extract metadata during HTML to Markdown conversion.

Authorkreuzberg-dev
Version1.0.0
Installs0

System Documentation

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.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: Metadata Extraction for html-to-markdown
Download link: https://github.com/kreuzberg-dev/html-to-markdown/archive/main.zip#metadata-extraction-for-html-to-markdown

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.