- Home
- Skills
- DevOps & Cloud
- Feed Watchdog
Works with the AI Agents you already use
Feed Watchdog
Monitor blogs, RSS and Atom feeds with the blogwatcher CLI: schedule polling, filter posts by keywords, dedupe repeats, push notifications and generate daily di
Free
Feed Watchdog
Example session with this skill installed
Set up a feed monitor for https://example.com/blog/rss that only alerts me on 'release' or 'update' via a webhook at http://localhost:8080/hook.
- Read your context and instructions
- Compiled the feed watchdog
- Installed
blogwatcher. - Initialized config at
~/.blogwatcher/config.yaml. - Added feed with filters:
include: "(release|update)" - Configured webhook notification.
- Started daemon:
blogwatcher watch --interval 15m --notify webhook=http://localhost:8080/hook --daemonize
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Monitoring dozens of RSS and Atom feeds manually is inefficient, and paid monitoring services are often overpriced for simple keyword alerting. Developers need a way to track specific content across blogs without noise or duplicate entries.
What it does
- Initializes and manages a local SQLite-backed feed workspace using the
blogwatcherCLI. - Filters incoming posts using regex-based include and exclude rules for titles and summaries.
- Handles automated polling with built-in deduplication based on post GUIDs.
- Triggers JSON webhooks for real-time alerts or generates Markdown digests for asynchronous review.
- Tracks feed statistics to monitor post volume and source activity over time.
Frameworks & tools
Python 3.9+, SQLite, RSS/Atom standards, and the blogwatcher CLI.
Why this beats prompting it yourself
Writing a script to handle feed polling requires solving edge cases like malformed XML, GUID deduplication, and state management. This skill provides a tested CLI workflow that manages the underlying database and notification logic out of the box.
Use cases
- Automate brand monitoring by alerting on keyword mentions across industry blogs.
- Create a curated daily digest of technical announcements for team review.
- Build a research pipeline that feeds new relevant articles into a custom webhook.
- Archive post history for specific tags to analyze publishing trends.
Known limitations
Does not support feeds behind authentication walls or sub-second market data requirements. Requires a persistent environment to run the background daemon.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for DevOps & Cloud.
Requires Python 3.9 or higher. Not suitable for feeds requiring authentication or real-time sub-second financial data. Persistent storage needed for the SQLite database.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
6 uses
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 3 months ago
- Free with an Agensi account
- Software
Python
Permissions
No special permissions declared or detected