agentsclimarketplace

R2 notebooklm artifact portal

Skill Sheshiyer/skill-clusters/skills/r2-notebooklm-artifact-portal

Hub-and-spoke agent-skill clusters, one per stack (Astro·GSAP·Remotion, Tauri, …). Installable via skills.sh.

Install
npx -y skills add Sheshiyer/skill-clusters --skill r2-notebooklm-artifact-portal

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when publishing, validating, or debugging public NotebookLM artifacts hosted on Cloudflare R2, including artifact inventories, public URLs, MIME types, cache headers, audio/video playback, and notebook visibility claims.

SKILL.md

2.3 KB, 492 tokens by cl100k_base, as published. Nobody here has run it

R2 NotebookLM Artifact Portal

Purpose

Validate that NotebookLM artifacts are real, public, correctly typed, cacheable, and usable from an Astro/wiki/press-kit portal.

Required Routing

  • Use notebooklm before claiming a notebook exists, sources are attached, or artifacts were generated.
  • Use cloudflare, wrangler, or cloudflare-manager for Cloudflare account/bucket operations.
  • Use this skill for the portal contract: public URLs, MIME, cache headers, inventory, embed/playback, and reader-facing labels.

Artifact Contract

Every portal artifact should have:

  • Stable id
  • Reader-facing title
  • Public href
  • type such as report, infographic, deck, audio, video, table, flashcard, quiz, or mindMap
  • Expected extension and MIME
  • Optional thumbnail
  • Reader-facing description

MIME Expectations

ExtensionExpected content type contains
.mp3audio/
.mp4video/
.pdfapplication/pdf
.pngimage/png
.csvtext/csv or application/octet-stream
.jsonapplication/json or application/octet-stream
.mdtext/, markdown, or application/octet-stream

Validation Workflow

  1. Check live NotebookLM visibility with notebooklm list --json or explicit notebook ID.
  2. Check local artifact inventory, usually src/data/artifacts.json.
  3. HEAD every remote artifact URL.
  4. Fail on 4xx/5xx, missing content type, incompatible MIME, or missing cache headers for large immutable assets.
  5. Verify audio/video pages use playable embeds or clearly labeled direct links.
  6. Verify public copy says Source artifact, Open artifact, or Download, not Raw artifact path.

Reader-Facing Copy Rules

  • Say NotebookLM companion artifact, not raw output.
  • Say R2-hosted source artifact, not local file path.
  • Do not expose bucket internals unless the URL itself is the public contract.
  • Do not claim NotebookLM flow completion without live account verification or an explicit local-only caveat.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.