Import sources (URLs, YouTube, files, text) into Google NotebookLM and generate artifacts: podcasts, videos, reports, quizzes, flashcards, mind maps, slide decks, infographics, data tables. Use when users want to study from web content, create learning materials from URLs or documents, generate quizzes from articles, or produce study aids.

GitHub
安装命令
npx skhub add bighardperson/notebooklm-studio
Markdown
SKILL.md

NotebookLM Studio

Import sources into NotebookLM, generate user-selected artifacts via CLI, download results locally.

Inputs

Collect from user message (ask only for missing fields):

  • Sources: URLs, YouTube links, text notes, or file attachments (PDF, Word, audio, image, Google Drive link)
  • Artifacts: User selects from 9 types (no default — always ask):
    • audio (podcast), video, report, quiz, flashcards, mind-map, slide-deck, infographic, data-table
  • Language (optional, default: zh_Hant): applied via notebooklm language set
  • Artifact options: format, style, length, difficulty, etc.
  • Custom instructions (optional): passed as description to generate commands

Workflow

Steps are sequential gates — do NOT skip or combine steps.

  1. Auth precheck — Verify the session is valid:

    notebooklm auth check --test --json
    
  2. Parse input & configure artifacts —

    • 1a. Select artifacts
    • 1b. Discuss options (ASK / OFFER / SILENT priority levels)
  3. Derive slug — Generate a short kebab-case slug for the notebook name and output directory.

  4. Create notebook —

    notebooklm create "<slug> <YYYYMMDD>"
    notebooklm use <notebook_id>
    mkdir -p ./output/<slug>
    
  5. Set language — notebooklm language set <confirmed_language>

  6. Add sources — For each source: notebooklm source add "<url_or_filepath>"

  7. Generate artifacts — Two-tier strategy:

    • Tier 1 (Immediate): mind-map, report, quiz, flashcards, data-table, infographic — use --wait
    • Tier 2 (Deferred): slide-deck, video, audio — use --json, capture task_id for polling
  8. Download Tier 1 — Each artifact into ./output/<slug>/

  9. Report + Deliver Tier 1 — Present completed artifacts to user

  10. Poll + Deliver Tier 2 — Wait for deferred artifacts, download and deliver as each completes

Artifact Types

TypeTierTypical Time
mind-map1Instant
report11-2 min
quiz11-2 min
flashcards11-2 min
data-table11-2 min
infographic12-5 min
slide-deck25-15 min
video210-30 min
audio (podcast)210-30 min

Requirements

  • notebooklm CLI (notebooklm-py)
  • ffmpeg (for audio compression)
  • playwright (for browser automation)

Error Handling

  • Auth errors: Caught by step 0 precheck. Re-login if expired.
  • Tier 1 failure: Retry up to 2 times, then include failure note in delivery.
  • Tier 2 failure: Notify user per-artifact. Tier 1 already delivered.
  • Timeout recovery: Never re-generate on timeout. Re-check status, re-wait if still processing.

Delivery Template

  1. Selection rationale (≤3 bullets)
  2. Artifact list with paths/status
  3. Key takeaways (3-5 bullets)
  4. Failures + fallback note (if any)
  5. One discussion question
发现
标签

此技能尚未发布标签。

版本
最新版本元数据

版本

v2026.09.24

发布时间

2026年9月24日

分类

未分类

许可证

NOASSERTION

源路径

skills/NotebookLM Studio

默认分支

main

最新提交

e9f99fd

Tree SHA

de4405f