blogwatcher

Monitor blogs and RSS/Atom feeds to track newly published articles and read/unread state.

Updated Apr 9, 2026

Search Tags:#sqlite #rss #atom #blog monitoring #feed discovery #opml import #article triage

Ready to run

npx skills add https://github.com/MarbleSodas/Mavis --skill blogwatcher-marblesodas

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: blogwatcher
Source: https://github.com/MarbleSodas/Mavis/tree/main/skills/research/blogwatcher
Command: npx skills add https://github.com/MarbleSodas/Mavis --skill blogwatcher-marblesodas

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Blog and RSS updates are easy to miss, forcing you to repeatedly check sites and manage new articles manually.

Core Features & Use Cases

Feed discovery & monitoring: Tracks blogs and RSS/Atom feeds, including automatic discovery from a homepage.
Scraping fallback: Uses HTML scraping when feed data isn’t available or fails, as long as you configure a selector.
Article management: Keeps read/unread state, supports category filtering, and can import subscriptions via OPML.

Use case: You follow several technical sites and want a reliable backlog of unread articles grouped by blog or category, so you can quickly triage what matters before it gets buried.

Quick Start

Run blogwatcher-cli scan to scan all tracked blogs and report how many new articles were found.

Frequently Asked Questions about blogwatcher

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

FAQPage Schema

How do I track RSS and Atom feeds for newly published articles?▼

You can track RSS and Atom feeds by running a scan across monitored blogs to identify newly published articles and persist their read or unread state in a SQLite database for reliable backlog triage.

Can I import OPML subscriptions for blog monitoring?▼

Yes, OPML import is supported to bulk import blog subscriptions, allowing you to immediately start feed monitoring, category-based filtering, and article triage within your workflow.

How does feed discovery work when a site does not publish RSS?▼

Feed discovery automatically detects RSS or Atom feeds from a homepage, and when feed data is unavailable, a configurable HTML scraping fallback extracts articles using a custom selector.

Do I need to install any dependencies to run blog monitoring scans?▼

You need the blogwatcher-cli command available in your environment to execute blog monitoring scans and manage article state, but no external software dependencies are explicitly required.

What is the best way to triage unread articles from multiple technical blogs?▼

The best way to triage unread articles is to group newly discovered posts by blog or category, filter based on your configured categories, and review the accumulated backlog periodically before articles get buried.