skills.rest
OldCoderIsMe
OldCoderIsMeCOMMUNITY
Explore all skills by this author →
GitHub

extract-metadata

Extract titles, authors, sources, dates, summaries, and tags from article URLs.

Updated Jan 27, 2026
Search Tags:#summarization#metadata extraction#tagging#content curation#claude ai#article analysis
One-click install
npx skills add https://github.com/OldCoderIsMe/AutoPaper --skill extract-metadata
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: extract-metadata
Source: https://github.com/OldCoderIsMe/AutoPaper/tree/main/claude-skills/plugins/extract-metadata
Command: npx skills add https://github.com/OldCoderIsMe/AutoPaper --skill extract-metadata

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anthropic, requests, readability-lxml, beautifulsoup4, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the tedious process of extracting key information from articles, saving you time and effort in content curation and analysis.

Core Features & Use Cases

  • Automated Metadata Extraction: Pulls titles, authors, sources, and publication dates from URLs.
  • Content Summarization & Tagging: Generates concise summaries and relevant tags for easy categorization.
  • Use Case: When curating a weekly tech newsletter, use this Skill to quickly gather essential details for each article, ensuring consistent formatting and rich content.

Quick Start

Use the extract-metadata skill to get the title and summary for the article at https://example.com/latest-ai-news.

Frequently Asked Questions about extract-metadata

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

FAQPage Schema
How do I extract article metadata like titles and authors from URLs?▼

To extract article metadata from URLs, this tool uses Claude AI to identify titles, authors, sources, and publish dates. You simply provide the article link, and the automated process returns the structured content details.

Can I generate summaries and tags for article content automatically?▼

Yes, you can generate summaries and tags automatically. The tool analyzes the article content using Claude AI to produce concise summaries and relevant tags for easy categorization and content curation.

What output formats are supported for extracted article metadata?▼

Extracted article metadata supports both JSON and Markdown output formats. This allows you to easily integrate the structured data into your content curation pipelines or documentation.

Does extracting metadata from URLs work with technical news articles?▼

Yes, extracting metadata works with technical news articles. The tool identifies article types, distinguishing between technical and news content, and extracts key points specific to the article format.

Do I need to install beautifulsoup4 and readability-lxml to parse article content?▼

Yes, you need beautifulsoup4 and readability-lxml installed to parse article content. These dependencies handle fetching and cleaning the HTML content before Claude AI extracts the structured metadata.

Related Skills

Explore More Content & Communication Skills→
Gimpy666Gimpy666
1

scraped_docs

Convert Tribot JavaDoc HTML pages into per-class Markdown files and a consolidated reference.

Community
Intermediate
OldCoderIsMeOldCoderIsMe

Extract Metadata Skill

Extract structured metadata, summaries, key points, and tags from article URLs.

Community
Intermediate
aresbitaresbit
46

summarize

Summarize URLs, local files, and video transcripts into concise summaries.

Community
Intermediate
TIAN0517TIAN0517

web-reader

Extract page title, HTML, text, and metadata from URLs via page_reader.

Community
Intermediate