rss-digest

Fetch RSS or Atom feeds and summarize the newest entries into a digest.

1.6k|168|Updated Dec 16, 2024
One-click install
npx skills add https://github.com/amd/gaia --skill rss-digest-amd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rss-digest
Source: https://github.com/amd/gaia/tree/main/hub/skills/rss-digest
Command: npx skills add https://github.com/amd/gaia --skill rss-digest-amd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Keeping up with blogs, release feeds, and news sites requires manually checking each source. This Skill fetches an RSS or Atom feed and produces a structured digest of the newest entries, so you can see what was published without visiting the site. ## Core Features & Use Cases - Feed Fetching and Parsing: Retrieves RSS 2.0 and Atom feeds through GAIA's WebClient and returns entries as structured data with title, link, published date, and summary. - Safe Error Reporting: Malformed feeds, 404s, blocked hosts, DTD-carrying feeds, and unsupported dialects like RSS 1.0/RDF are reported as explicit errors rather than silent empty digests. - Security-Conscious Parsing: Refuses feeds declaring a DTD to prevent entity expansion denial-of-service attacks, and blocks private or loopback addresses via built-in SSRF guards. - Use Case: Ask for a digest of a project's release feed to quickly spot a security release or breaking change among routine updates, with the exception highlighted first. ## Quick Start Summarize the latest entries from the feed at https://example.com/feed.xml and highlight anything unusual.

Frequently Asked Questions about rss-digest

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

FAQPage Schema
How do I summarize an RSS feed with an AI agent?

Provide the feed URL and the fetch_rss tool retrieves the feed, returning entries with title, link, published date, and summary. The agent then writes a one-line digest per entry, grouping by theme and highlighting any exceptional item first.

What feed formats does RSS parsing support?

RSS 2.0 and Atom feeds are supported, with Atom namespaces stripped so one parser handles both. RSS 1.0/RDF feeds are not supported and return an explicit error rather than an empty digest.

Why does feed parsing fail with a DTD error?

Feeds declaring a DOCTYPE are refused because entity expansion is a denial-of-service vector and no real feed needs a DTD. Only the prolog is scanned, so DOCTYPE-like text inside entry content does not trigger the refusal.

Can I fetch feeds from private or localhost addresses?

No. The tool fetches through GAIA's WebClient, which refuses private and loopback addresses as SSRF protection. Point it at a public HTTP or HTTPS feed URL.

Why does a valid URL return an error instead of entries?

Errors are returned verbatim for malformed XML, 404s, unreachable hosts, feeds with no recognizable entries, or unsupported dialects. The URL may point at an HTML page rather than a feed, which is reported rather than guessed.