agentleFS
ArgentAIOSArgentAIOS/agent-skills/notebooklm-research/SKILL.md

notebooklm-research

Skill4 starsChanged 8 months agoMITView on GitHub

Run YouTube-driven research in ArgentOS by searching videos and sending links into NotebookLM for synthesis and infographic outputs via youtube_notebooklm.

  • Installs packages

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 4 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use youtube_notebooklm when the user wants market research, trend mapping, competitor scans, or synthesis from YouTube sources through …

    line 16
  2. Very specific:

    Use youtube_to_notebook_workflow for end-to-end execution:

    line 20
  3. Distinctive:

    Add videos as sources

    line 24
  4. Distinctive:

    Ask NotebookLM for analysis

    line 25
  5. Very specific:

    Call setup_status first. If setupRequired: true, run the returned next_steps commands before continuing.

    line 30
  6. Distinctive:

    Use granular actions if the user wants custom sequencing or to reuse an existing notebook.

    line 58
  7. Distinctive:

    If commands fail, report missing prerequisites and suggest the exact install/login command.

    line 71
  8. Very specific:

    Default recency filter is last 6 months (months: 6).

    line 75
  9. Very specific:

    Keep wait_for_sources: true for reliable downstream analysis.

    line 77

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

NotebookLM Research

Use youtube_notebooklm when the user wants market research, trend mapping, competitor scans, or synthesis from YouTube sources through NotebookLM.

Primary Action

Use youtube_to_notebook_workflow for end-to-end execution:

  1. Search YouTube
  2. Create NotebookLM notebook
  3. Add videos as sources
  4. Ask NotebookLM for analysis
  5. Optionally generate/download infographic

First-run check:

  • Call setup_status first. If setupRequired: true, run the returned next_steps commands before continuing.

Fast Start

{
  "action": "youtube_to_notebook_workflow",
  "query": "Claude Code skills marketing",
  "count": 10,
  "months": 6,
  "question": "What are the strongest recurring GTM patterns and differentiators across these videos?",
  "generate_infographic": true,
  "infographic_prompt": "Create a handwritten blueprint style infographic with GTM patterns, risks, and opportunities.",
  "infographic_orientation": "portrait",
  "infographic_detail": "detailed"
}

Granular Actions

  • youtube_search
  • setup_status
  • notebook_create
  • notebook_add_sources
  • notebook_ask
  • notebook_generate_infographic

Use granular actions if the user wants custom sequencing or to reuse an existing notebook.

Prerequisites

Install dependencies once:

pip install yt-dlp
pip install "notebooklm-py[browser]"
playwright install chromium
notebooklm login

If commands fail, report missing prerequisites and suggest the exact install/login command.

Operating Notes

  • Default recency filter is last 6 months (months: 6).
  • Set no_date_filter: true to include all upload dates.
  • Keep wait_for_sources: true for reliable downstream analysis.
  • For stakeholder-ready output, enable generate_infographic and keep the prompt specific.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.