How does this differ from standard URL extraction?

Unlike standard tools that extract every link, this skill identifies the 'central source,' such as a main blog page or a user's GitHub profile, rather than specific sub-pages.

Is this skill useful for SEO and marketing research?

Absolutely; it helps researchers quickly identify the primary domains and authoritative sources that are being cited within a specific niche or article.

Can it handle social media profiles?

Yes, if a person is mentioned as a source, the skill is designed to link to their primary profile provided in the input text.

What is the output format of the extracted domains?

The skill produces a clean, deduplicated list with exactly one source URL per line and no additional conversational text.

Domain and Source Extractor

Name: Domain and Source Extractor
Author: bdmorin

bybdmorin

•

Web Scraping & Data Collection

Identifies and extracts primary source domains, GitHub profiles, and publication URLs from articles and newsletters.

The extract-domains skill allows Claude Code to intelligently map the information landscape of any text input, such as research papers, newsletters, or blog posts. Instead of merely listing every hyperlink found, it focuses on identifying the 'central source' of stories—such as a company's base blog URL, a researcher's profile, or a main GitHub repository. This is particularly useful for content curators, researchers, and developers who need to discover new authoritative sources to follow or verify the origins of specific information within a document.

Key Features

011 GitHub stars

02Identifies central source domains rather than just raw deep-links

03Optimized for analyzing newsletters and multi-story articles

04Automatically deduplicates sources to provide a clean list

05Outputs standardized, single-line URLs for easy programmatic use

06Handles diverse source types including GitHub, company blogs, and academic publications

Use Cases

01Mapping the primary sources used in a competitor's research paper

02Building a 'who-to-follow' list based on industry news roundups

03Cleaning up messy reference lists into standardized domain URLs

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add bdmorin/the-no-shop extract-domains

For use in Claude.ai and ChatGPT

Key Features

011 GitHub stars

02Identifies central source domains rather than just raw deep-links

03Optimized for analyzing newsletters and multi-story articles

04Automatically deduplicates sources to provide a clean list

05Outputs standardized, single-line URLs for easy programmatic use

06Handles diverse source types including GitHub, company blogs, and academic publications

Use Cases

01Mapping the primary sources used in a competitor's research paper

02Building a 'who-to-follow' list based on industry news roundups

03Cleaning up messy reference lists into standardized domain URLs

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add bdmorin/the-no-shop extract-domains

For use in Claude.ai and ChatGPT