원클릭으로
get-notebooklm-video
Download a NotebookLM video artifact to /input/video.mp4 and create a title.json with its title.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Download a NotebookLM video artifact to /input/video.mp4 and create a title.json with its title.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
[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.
Overview of the Panda Video Automation pipeline — from NotebookLM research to video upload. Run this skill to see the full workflow.
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 | get-notebooklm-video |
| description | Download a NotebookLM video artifact to /input/video.mp4 and create a title.json with its title. |
Download a completed video artifact from a notebook to the local input directory.
Note: Use
notebooklm download video(top-level command), NOTnotebooklm artifact download(does not exist).
notebooklm artifact list -n <notebook-id> --json
Download to /input/video.mp4:
notebooklm download video -n <notebook-id> -a <artifact-id> input/video.mp4 --force
Options:
--force — overwrite existing file--no-clobber — skip if file exists--all — download all video artifacts-a / --artifact <id> — select by artifact ID (supports partial match)--name "<title>" — select by artifact title (fuzzy match)echo '{"title": "<video-title>"}' > /input/title.json
NotebookLM-generated videos often include an ending bumper/logo frame. Trim the last 3 seconds from the video to clean it up:
# Get video duration in seconds
DURATION=$(ffprobe -v error -show_entries format=duration \
-of default=noprint_wrappers=1:nokey=1 "input/video.mp4")
# Calculate new duration (minus 3 seconds)
TRIM_TO=$(echo "$DURATION - 3" | bc)
# Cut video to new duration (fast — stream copy, no re-encode)
ffmpeg -i "input/video.mp4" -t "$TRIM_TO" -c copy \
"input/video-trimmed.mp4"
# Replace original with trimmed version
mv "input/video-trimmed.mp4" "input/video.mp4"
echo "Trimmed last 3s: ${DURATION}s → ${TRIM_TO}s"
Requires
ffmpegandffprobe. Install viabrew install ffmpeg(macOS) orapt install ffmpeg(Linux).
input/
├── video.mp4 (typically ~50-100MB, last 3s trimmed)
└── title.json