NotebookLM Content Creation (J-Claw)

---

name: notebooklm-content-creation description: "Create and monitor NotebookLM Studio content — Audio Overview, Video Overview, Infographics, and Slides — via the notebooklm-mcp-cli. Use when user wants to generate a podcast, video, infographic, or slide deck from a NotebookLM notebook. Also triggered by upstream skills (e.g., Deep Research) with pre-filled parameters. Triggers on: create audio, create video, create infographic, create slides, generate podcast from notebook, make a video overview, notebooklm studio create, download notebook audio, notebooklm content creation, 请启动 NotebookLM 工作流. Requires notebooklm-mcp-cli installed and authenticated."

---

NotebookLM Content Creation

Creates NotebookLM Studio content (Audio Overview, Video Overview, Infographics, Slides) and monitors it to completion using a background polling loop.

Requires:

notebooklm-mcp-cli installed: uv tool install notebooklm-mcp-cli

Authenticated: nlm login (done on the server already)

---

Studio Types

| Type | Command | Formats | Lengths | Notes | |------|---------|---------|---------|-------| | Audio Overview | nlm audio create | deep_dive, brief, critique, debate | short, default, long | ✅ confirmed working | | Video Overview | nlm video create | explainer, brief, cinematic | — | ⚠️ NOT nlm studio create --type video | | Infographics | nlm infographic create | — | — | ⚠️ NOT nlm studio create --type infographic | | Slides | nlm slides create | detailed_deck, presenter_slides | short, default | ⚠️ NOT nlm studio create --type slides |

⚠️ CLI 与 SKILL 旧版不一致（重要！）

nlm studio create 不支持 --type 参数！每种产出类型是独立的顶级命令：

nlm video create --format explainer --language zh-CN --confirm

nlm infographic create --detail detailed --orientation landscape --language zh-CN --confirm

nlm slides create --format detailed_deck --length default --language zh-CN --confirm

⚠️ Download 命令

Audio: nlm download audio --id -o

Video: nlm download video --id -o

Infographic: nlm download infographic --id -o

Slides: nlm download slide-deck --id -o ⚠️ 不是 nlm download slides！

---

Workflow

Step 1 — Notebook Selection

List all notebooks:

nlm notebook list

Parse the JSON output for id and title. Match against the user's keyword (case-insensitive substring match). If multiple match, present options with numbers.

If no notebook matches:

Ask user: "No notebook found matching '[keyword]'. Create a new one or add more sources to an existing notebook?"

If user confirms new notebook: create with nlm notebook create ""

Then add sources: nlm source add --url --wait

Step 2 — Check Existing Artifacts

Before creating new content, check if the notebook already has generated artifacts:

nlm studio status 

If artifacts with status: completed exist, show them to the user and ask: > "This notebook already has completed content. Download existing [type] or generate new content?"

Download existing: go directly to download step

Generate new: proceed to Step 3

Step 3 — Pre-Flight Confirmation OR Auto-Execute

Interactive mode (user initiated): Ask all parameters at once. Write in the user's current session language.

Creating [Audio/Video/Infographic/Slides] Overview from "[notebook name]"
Please confirm:
① Content type: [Audio Overview / Video Overview / Infographics / Slides]
② Format: [deep_dive / brief] (default: deep_dive)
③ Length: [short / default / long] (default: default) — not available for Infographics/Slides
④ Language: [BCP-47 code, e.g., en, zh-CN] (default: notebook's detected language or en)
⑤ Output path: [path] (default: ~/ObsidianVault/Default/NotebookLM//)
Reply with any changes, or "ok" to proceed with defaults.

Triggered mode (upstream skill chaining): When the agent receives a trigger message containing all required parameters (e.g., from Deep Research), skip user confirmation and auto-execute. The trigger message should include:

报告路径 / report_path: path to the source file to upload

Notebook 名称 / notebook_name: name for the notebook (create if not exists)

产出类型: Audio Overview / Video Overview / Infographics / Slides

格式: deep_dive / brief / etc.

长度: short / default / long

语言: BCP-47 code

In triggered mode, the agent should: 1. Create notebook with nlm notebook create "" 2. Upload source with nlm source add --file --wait 3. Proceed directly to Step 4 (Create Content) with the provided parameters 4. Set up polling and notify user when complete

Step 4 — Create Content

Based on user's confirmed parameters:

Audio:

nlm audio create  --format  --length  --language  --confirm

Capture the returned Artifact ID.

Video:

nlm video create  --format  --style