Skip to content
TrustedSkillsbeta
Back to all skills

Notebooklm

Checked
davila7·vlatest·data·MIT

Notebooklm allows users to seamlessly integrate AI models directly into their Jupyter notebooks for interactive experimentation and analysis.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add davila7/claude-code-templates --skill notebooklm -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

davila7

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned davila7/claude-code-templates at 79182c51fb.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
79182c51fb
Manifest
cli-tool/components/skills/ai-research/deep-research-notebooklm/SKILL.md
Scanned
2 files, 191 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

The NotebookLM skill integrates Google's NotebookLM AI directly into your workflow, allowing agents to ingest and analyze custom documents, audio files, and web links in real time. It functions as a specialized research engine that synthesizes information from your provided sources rather than relying solely on general training data.

When to use it

  • Conducting deep-dive analysis on proprietary internal reports or confidential datasets not available online.
  • Summarizing lengthy transcripts from recorded meetings, podcasts, or interviews into actionable bullet points.
  • Generating quiz questions and study guides based exclusively on specific textbook chapters or research papers you upload.
  • Extracting key insights and cross-referencing facts across multiple simultaneous documents to ensure accuracy.

Key capabilities

  • Ingests diverse file types including PDFs, text files, Google Docs, spreadsheets, and audio recordings.
  • Synthesizes answers by strictly adhering to the context of uploaded source materials.
  • Generates creative outputs such as quizzes, summaries, and rewritten content based on your inputs.
  • Provides citations linking generated insights back to specific parts of your source documents.

Example prompts

  • "Read these three PDFs about quantum computing and summarize the current consensus on error correction methods."
  • "Create a 10-question multiple-choice quiz based on the attached lecture transcript, including the correct answers and explanations."
  • "Rewrite this long technical manual into a concise executive summary suitable for non-technical stakeholders."

Tips & gotchas

Ensure your uploaded files are text-readable or transcribed audio; binary-only formats may not be processed correctly. The AI's accuracy is strictly bounded by the quality and clarity of the documents you provide, so verify critical facts against the original sources before finalizing decisions.