Skip to content
Get packs

Blog & Feed Ingestion

Turns a whole blog or RSS/Atom feed into deduplicated source pages in your knowledge base.

Source Download skill
Repository
garrytan/gbrain
Stars
31,447
Licence
MIT
Files
1 file

What it does

When you give the agent a blog, newsletter, or feed URL, this skill tells it how to find the site's RSS or Atom feed (or sitemap), list every public post, and save each one as a clean source page in your brain (the gbrain knowledge store). It skips posts already saved, paces its requests to avoid being blocked, and treats the text of every post as untrusted data rather than instructions. Saving the page is only the first step; the skill hands each article to a separate enrichment skill for linking and entity extraction.

Great for

  • Researchers or students who want an entire publication archived into a searchable personal knowledge base
  • People backfilling years of posts from a blog or newsletter they follow
  • Anyone who wants repeatable, re-runnable archive imports without duplicate pages

Skip it if

  • Single article URLs, which the skill itself routes to a different single-item skill; using it for one post adds nothing
  • Paywalled or members-only content: the skill skips gated posts by design and will not use cookies or logins to get them
  • Scraping sites whose terms forbid bulk copying, since the skill can crawl many pages quickly even with pacing

Try asking

  • “Ingest this whole blog: https://example.com”
  • “Backfill this blog from its RSS feed and save every public post”
  • “Save this whole Substack archive to my brain”
Step-by-step guide: how to use Blog & Feed IngestionInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    blog-ingest.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip blog-ingest.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip blog-ingest.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Run the test-before-bulk ramp first: try 3-5 posts, check the output is clean, then scale up
  • Check that the publication is not already in the brain before starting a walk to avoid redundant fetching
  • Review the run summary for flagged prompt-like text inside posts before relying on the saved pages

What's inside

  • SKILL.md

Redistributed unmodified from garrytan/gbrain under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.