What file formats are supported for output?

The skill provides structured JSON by default for programmatic use and a clean Markdown format for human-readable documentation.

Does this skill require an API key?

Yes, it requires an Anthropic API key to perform the intelligent content analysis and metadata extraction.

Can I customize the AI model used?

Absolutely. You can specify different Claude models or custom API endpoints via the ANTHROPIC_MODEL and ANTHROPIC_BASE_URL environment variables.

How does the caching mechanism work?

It stores results locally for 7 days by default, preventing duplicate API calls for the same URL to save on costs and improve performance.

Can I use it on raw text instead of a URL?

Yes, you can pass raw content using the --content flag, which skips the web scraping phase and proceeds directly to AI analysis.

Article Metadata Extractor

Name: Article Metadata Extractor
Author: OldCoderIsMe

byOldCoderIsMe

0•

ウェブスクレイピングとデータ収集

Extracts structured metadata, summaries, and key points from web articles or raw text using AI-powered analysis.

This skill automates the transformation of unstructured web content into rich, structured data formats like JSON or Markdown. It leverages Claude's advanced reasoning to accurately identify authors, publication dates, and core themes while generating concise summaries and intelligent tags. Built-in caching and retry mechanisms ensure high performance and reliability, making it an essential tool for developers building news aggregators, knowledge management systems, or automated content analysis workflows.

主な機能

01Smart categorization and tagging (e.g., technical vs. news)

02Flexible output formats supporting both JSON and Markdown

03Automated extraction of title, author, source, and publication date

04Robust 7-day TTL caching mechanism to minimize API costs

05AI-generated concise summaries and 3-7 core key points

060 GitHub stars

ユースケース

01Automating content tagging and classification for CMS workflows

02Enriching personal knowledge bases with structured metadata and summaries

03Building automated news aggregators or newsletter generation tools

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add oldcoderisme/autopaper extract-metadata

For use in Claude.ai and ChatGPT

主な機能

01Smart categorization and tagging (e.g., technical vs. news)

02Flexible output formats supporting both JSON and Markdown

03Automated extraction of title, author, source, and publication date

04Robust 7-day TTL caching mechanism to minimize API costs

05AI-generated concise summaries and 3-7 core key points

060 GitHub stars

ユースケース

01Automating content tagging and classification for CMS workflows

02Enriching personal knowledge bases with structured metadata and summaries

03Building automated news aggregators or newsletter generation tools

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add oldcoderisme/autopaper extract-metadata

For use in Claude.ai and ChatGPT