Fetch and digest any RSS or Atom feed with zero API keys — curl plus disciplined parsing into a ranked, deduplicated briefing instead of a link dump. Use when asked summarize this feed, what's new on this blog, digest these RSS feeds, or build me a morning briefing from these sources. Produces the digest with dates and one-line what-it-is summaries, cross-feed dedup, and the rerunnable commands per feed.
Start a fresh conversation. Replace the highlighted placeholders.
Use rss-digest to produce a dated, deduplicated briefing from [feed URLs or sites] covering [time window], filtered to [topic lens]; summarize substance rather than titles and note any feeds that cannot be fetched.
Required inputs
[feed URLs or sites]
[time window]
[topic lens]
User-approved starter prompt based on a pinned source version; check current skill requirements before running. Task evidence ↗
SKILL.md
name: rss-digestdescription: "Fetch and digest any RSS or Atom feed with zero API keys — curl plus disciplined parsing into a ranked, deduplicated briefing instead of a link dump. Use when asked summarize this feed, what's new on this blog, digest these RSS feeds, or build me a morning briefing from these sources. Produces the digest with dates and one-line what-it-is summaries, cross-feed dedup, and the rerunnable commands per feed."
RSS Digest Skill
RSS never died — every blog, newsroom, podcast, release page, and status page still speaks it, keylessly, and it remains the cleanest way for an agent to answer "what's new from the sources I care about." This skill fetches feeds with curl, parses the two dialects (RSS 2.0 and Atom) without ceremony, and produces what the user actually wanted: a dated, deduplicated briefing with one line of substance per item — not thirty titles.
What This Skill Produces
The digest — items with date, source, title, and a one-line what-it-actually-says from the item's own description
Cross-feed dedup — the same story via three feeds appears once, sources noted
The since-filter — "what's new" means since the user last asked or a stated window, applied
The commands — one curl per feed, rerunnable
Required Inputs
Ask for these if not provided:
The feed URLs — or the site ("find the feed" is part of the job: try /feed, /rss, /atom.xml, /index.xml, and the <link rel="alternate" type="application/rss+xml"> tag in the page head)
The window — today, this week, since a date — "what's new" needs an epoch
The lens — everything, or filtered to a topic; a briefing has a reader, and the reader has interests
Framework: Fetch, Parse, Digest
The fetch:curl -sL "https://hnrss.org/frontpage" — follow redirects (-L), and identify politely if a feed rejects default agents (-A "rss-digest/1.0"). Feeds are XML; both dialects carry the same essentials: RSS <item><title><link><pubDate><description> · Atom <entry><title><link href><updated><summary/content>.
Parse without heroics: items are extracted with straightforward pattern-matching on those tags; HTML inside descriptions gets stripped to text; entities decoded. Malformed feeds (common) get a best-effort parse and an honest note, not a crash or silent gaps.
The one-line rule: each item's line comes from its description/summary content — what the piece actually says — not a restatement of its title. When the description is empty or useless, say what can be said from the title and mark it thin; fetch the full article only if the user asks for a deep-dive on an item.
Dedup and order: same-story detection across feeds by normalized title/URL similarity; ordering is newest-first within the window, or grouped by source when the user's mental model is per-source.
Honest dating:pubDate/updated converted to the user's zone; items without dates are labeled undated, not invisibly slotted; and the digest states its own window ("covering the last 48h as of [time]").
Output Format
Digest: [N sources] — [window], as of [time]
[If a lens was set: the matching items first.]
[Source A]
[date] [title] — [one line of what it says] ([link])
[…]