Can I scrape articles published before November 2025?

Yes, while the default is set to 2025-11-01, you can use the --since YYYY-MM-DD argument to specify an earlier cutoff date.

What is required to use this skill?

You must have the Firecrawl MCP server connected and configured within your Claude Code environment to handle the web extraction tasks.

Does the scraper remove ads and newsletter popups?

Yes, it includes specific cleanup patterns to remove promotional footers, sponsor mentions (like WorkOS), and inline reading time indicators to provide clean technical text.

How does this skill save on Firecrawl API costs?

It implements an optimization step that scans the blog's main listing page first to identify which posts are new or updated, only performing full article scrapes when necessary.

Milan Jovanovic Blog Scraper

Name: Milan Jovanovic Blog Scraper
Author: melodic-software

bymelodic-software

•

网络抓取与数据收集

Extracts and cleans the latest .NET development articles from Milan Jovanovic's blog with an optimized, cost-effective workflow.

This skill automates the process of staying updated with Milan Jovanovic's .NET blog by intelligently scraping new content directly into your workspace. It utilizes a multi-step optimization process that scans the main blog listing first to identify new posts, drastically reducing API calls and Firecrawl usage. The skill automatically strips promotional footers, sponsor mentions, and social media clutter, leaving you with clean, markdown-formatted technical articles ready for local indexing, AI-assisted learning, or RAG applications.

主要功能

01Flexible filtering using date-based constraints and limit arguments

02Optimized pre-filtering from listing pages to minimize Firecrawl API consumption

03Structured storage of technical content in canonical markdown format

0438 GitHub stars

05Content hashing to intelligently skip updates for unchanged articles

06Automated cleaning of promotional content, sponsors, and newsletter footers

使用场景

01Building a local, searchable library of expert .NET technical articles

02Keeping a development environment synchronized with the latest .NET patterns and best practices

03Automating content ingestion for local AI knowledge bases or documentation tools

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add melodic-software/claude-code-plugins scrape-posts

For use in Claude.ai and ChatGPT

Download Skill