RSS Feed Aggregator and Summarizer
Paste the following prompt into your AI chat to install this skill:
Please install @user_82a39fde/mrbank-rss-aggregator according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem
Engineers often track Hacker News, arXiv, GitHub Trending, and sspai at once, but each source updates on its own cadence. Manual refreshing misses items, and there is no consistent place to filter keywords or compare feeds.
How It Works
The skill treats RSS 2.0, Atom, and JSON Feed as one input, parses non-standard feeds with feedparser, and fetches multiple sources concurrently. It supports parameters such as --source, --category, --keywords, --exclude, --author, and --tag, so you can browse tech, programming, AI, and finance categories, keep items matching AI,GPT, and exclude noise. Results default to date-descending order, while --limit, --content, and --json control output density, making it useful for terminal workflows or downstream summarization.
Boundaries
This is better for structured news flows than for close reading or deep research. Custom RSS URLs are supported, but output quality still depends on source formatting, anti-scraping behavior, and update reliability. If you need archiving, push delivery, or long-term retrieval, pipe the --json output into a downstream pipeline.
Use Cases
- Subscribe to Hacker News and TechCrunch each morning, then filter model updates with --keywords AI
- Follow Ruanyifeng Weekly by using --author and --limit to inspect only the latest ten items
- Browse tech and programming categories, then remove Mac-related noise with --exclude
- Export GitHub Trending and arXiv CS.AI as --json and feed the output into a weekly report script
Best For
- Engineers who need to pick technical signals from Hacker News, arXiv, and GitHub Trending daily
- Content editors who compile AI, tech media, and open-source updates into weekly reports
- Automation engineers who batch-fetch RSS feeds and filter keywords from the terminal
- Researchers who track technical news without manually opening multiple sites
Related Skills
Automatically compiles Feishu documents with quality checks, deduplication, Wiki updates, and multidimensional table index writes.
Open-ended visual QA for images, combining CV and LLM for scene description, chart interpretation, reasoning, and cloud history lookup.
Fast CLI for summarizing URLs, local files, and YouTube links with multi-provider models and JSON output.
Extracts an eight-layer reasoning fingerprint from scholar texts and applies a nine-module constraint to run peer review, supervision, lecturing, or panel discussion with quantitative scores and qualitative comments.