メニュー
Overview of the Panda Video Automation pipeline — from NotebookLM research to video upload. Run this skill to see the full workflow.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
[ENTRY POINT] Full NotebookLM pipeline — research → generate video → download → watermark → trim → generate meta files → cover → prepare upload → publish. Single entry point for all end-to-end video tasks.
Cross-platform video upload (login only when explicitly requested) — Bilibili, Douyin, Kuaishou, Weixin Video, YouTube
Research a topic with NotebookLM — create notebook, run deep research, auto-import sources, and summarize. Checks notebooklm installation, login, and skill installation first.
Create a NotebookLM notebook for a topic and generate a video overview in Simplified Chinese. Delegates installation and login checks to notebooklm-research skill.
Download a NotebookLM video artifact to /input/video.mp4 and create a title.json with its title.
Generate minimalist academic-style cover images via Python/Pillow — black (#000000) solid background, centered bold white title (120px), thin subtitle (76px) below. ONLY text on black — no graphics, icons, dates, or logos. TRIGGER: activates when user mentions "simple cover", "minimalist cover", "academic cover", or "cover" without further qualifiers. For "detailed cover", "complex cover", "report-style cover", or "detailed cover"/"complex cover", do NOT use this skill — instead generate a detailed infographic with --style professional or --style scientific.
| name | setup-pva-notebooklm |
| description | Overview of the Panda Video Automation pipeline — from NotebookLM research to video upload. Run this skill to see the full workflow. |
This project automates the full pipeline: research a topic via NotebookLM → generate AI video → prepare for upload → publish to platforms.
npm install -g @panda-video-automation/pva
pva --version
Also ensure notebooklm-py is installed:
pip install notebooklm-py
notebooklm skill install
Each step below resolves immediately (background work). Wait times are noted.
Creates a NotebookLM notebook and starts deep web research.
notebooklm create "<topic>" --json
notebooklm use <notebook-id>
notebooklm source add-research "<query>" --mode deep --no-wait
Wait ~5 min — run notebooklm research wait --import-all to finish and auto-import all sources.
Generates a video overview in Simplified Chinese from the notebook.
notebooklm generate video "<title> video overview" --language zh_Hans --format explainer --style auto --no-wait --json
Wait ~5 min — check back and download the video via /get-notebooklm-video.
/skill get-notebooklm-video
Downloads video to /input/video.mp4 with title.json.
Moves video and title into the structure expected by upload scripts.
/skill notebooklm-prep-upload
Uploads to Bilibili, Douyin, Kuaishou, Weixin Video, or YouTube.
/skill pva-publisher
| Skill | What it does |
|---|---|
/pva-check | Verify all prerequisites |
/setup-pva-notebooklm | This overview |
/notebooklm-research | Research a topic via NotebookLM |
/notebooklm-video | Research + generate video |
/get-notebooklm-video | Download video artifact |
/notebooklm-prep-upload | Prepare video for upload |
/pva-publisher | Cross-platform upload |
Note: Each step launches background work and resolves immediately. The user should wait the indicated time before proceeding to the next step.