daily-news-watcher

Track named news sources and generate Markdown digests with SQLite storage.

325|60|Updated Apr 20, 2026
One-click install
npx skills add https://github.com/Prompthon-IO/agent-systems-handbook --skill daily-news-watcher
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: daily-news-watcher
Source: https://github.com/Prompthon-IO/agent-systems-handbook/tree/main/skills/daily-news-watcher
Command: npx skills add https://github.com/Prompthon-IO/agent-systems-handbook --skill daily-news-watcher

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires feedparser, playwright, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Track named news sources over time with a persistent local store.

Core Features & Use Cases

  • Persistently track multiple sources across runs
  • Deduplicate and summarize recent articles into a Markdown report
  • Support two workflows: Add sources and Fetch & Summarize

Quick Start

Register your sources once, then run the fetch task to generate a Markdown digest.

Frequently Asked Questions about daily-news-watcher

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

FAQPage Schema
How do I track RSS feeds and generate a daily news digest without duplicating articles?

Track RSS feeds persistently by storing fetched articles in a local SQLite database. Deduplication across runs ensures only unique recent articles appear in the generated Markdown digest.

How do I monitor AI and tech news from multiple sources over time using a local store?

Monitor AI and tech news by registering named sources with a CLI. The tool fetches the latest 24 hours of content and uses a persistent local store to maintain tracking history across runs.

Can I use Playwright to fetch news content and filter results by topic and time?

Playwright fetches news content from registered sources. A CLI applies topic and time filters to the fetched articles, allowing you to narrow results before generating a per-run Markdown report.

What is the best way to deduplicate news articles across multiple fetch runs?

Deduplicate news articles by storing fetched items in a SQLite database under ~/.codex/state. This persistent store tracks seen articles across runs, preventing duplicates in the final Markdown digest.

Does this news watcher require manually setting up a database before fetching RSS feeds?

No manual database setup is required. The tool automatically initializes a SQLite database under ~/.codex/state/daily-news-watcher to persistently track sources and articles across runs.