NotebookLM Skill
NotebookLM Skill is a third-party Claude Code package that drives NotebookLM through a local browser, not Google's product page. Rechecked 2026-08-18: github.com/PleasePrompto/notebooklm-skill had 7,639 stars, license MIT, default branch master. README says it works only with local Claude Code, not the web UI sandbox. SKILL.md tells the agent to query uploaded notebooks for source-grounded Gemini answers via python scripts/run.py. There is no skill dollar seat.
Compare NotebookLM if you wanted the Google product, Claude Skills if you wanted how SKILL.md loads, and Post to WeChat if you wanted another third-party skill.
Key Features
- Local Claude Code only: First-party README. Do not sell this as a claude.ai web skill.
- Browser automation, not an official API: Each question opens a session against your NotebookLM library. Auth is persistent per AUTHENTICATION.md.
- Wrapper is required: SKILL.md says never call scripts directly; always
python scripts/run.py. - Based on notebooklm-mcp: README badge points at PleasePrompto/notebooklm-mcp as the sibling.
Use Cases
- People who already keep sources in NotebookLM and want Claude Code to ask them.
- People who can run a local browser + Python 3.8+.
- People who should open NotebookLM first if they do not have a notebook yet.
Limitation: Google can change the NotebookLM UI and break the automation. This is not an official Google skill.
Pricing
GitHub on 2026-08-18.
| Piece | Price | Notes from first-party pages |
|---|---|---|
| notebooklm-skill | $0 | MIT. 7,639 stars. |
| NotebookLM / Google account | Recheck Google | The product is separate. |
| Claude Code | Recheck that product | Local CLI required. |
If a leftover blog still treats this repo as Google NotebookLM itself, treat this table as the source.
Getting Started
- Open github.com/PleasePrompto/notebooklm-skill on the master branch.
- Recheck NotebookLM for the Google product.
- Recheck Claude Skills for install.
- Do not try this in the Claude web sandbox.
Frequently Asked Questions
Is this NotebookLM?
No. NotebookLM is Google's product. This is a MIT skill that automates it.
Does it work in Claude chat on the web?
README says no. Local Claude Code only.
Same as Anthropic example skills?
No. Those are in anthropics/skills. This is PleasePrompto.
Alternatives
- NotebookLM: The Google product.
- Claude Skills: How skills load.
- Post to WeChat: Another third-party publishing skill.
Tips
- Quote 7,639 stars, MIT, and local-only from the README.
- Always wrap scripts with
run.py. - Recheck AUTHENTICATION.md before you assume login persists forever.
Conclusion
NotebookLM Skill is a 7,639-star MIT local Claude Code helper for Google NotebookLM, not the NotebookLM product. Start at github.com/PleasePrompto/notebooklm-skill, then decide whether NotebookLM already covers the notebook itself.
Comments
No comments yet. Be the first to comment!
Related Tools
Algorithmic Art Skill
github.com/anthropics/skills/tree/main/skills/algorithmic-art
Anthropic example skill. Rechecked: p5.js philosophy + HTML/JS in anthropics/skills, 169,913 stars. Not a generative studio.
Canvas Design Skill
github.com/anthropics/skills/tree/main/skills/canvas-design
Anthropic example skill. Rechecked: philosophy then PNG/PDF in anthropics/skills, 169,913 stars. Not a design SaaS.
Doc Co-Authoring Skill
github.com/anthropics/skills/tree/main/skills/doc-coauthoring
Anthropic example skill. Rechecked: three-stage doc workflow in anthropics/skills, 169,913 stars. Not a paid writer.
Related Insights
Skills + Hooks + Plugins: How Anthropic Redefined AI Coding Tool Extensibility
An in-depth analysis of Claude Code's trinity architecture of Skills, Hooks, and Plugins. Explore why this design is more advanced than GitHub Copilot and Cursor, and how it redefines AI coding tool extensibility through open standards.
Claude Code's Next Frontier: Not Code, But Your Local Obsidian Knowledge Base
Explore how Obsidian + Claude Code transforms from a knowledge management tool into your private AI assistant. Complete guide including obsidian-skills, Claudian plugin, Claudesidian template, and best practices for achieving both data privacy and AI capabilities.
Seven AI Coding CLIs, Six Months: No Matter How Strong the Model, Work Needs Supervision
Claude Code, Codex, opencode, pi, omp and DeepSeek Harness all have personalities. After six months of deep use I run a division of labor: pi for the fastest cheapest reviews, omp for complex PRs, DeepSeek Harness on V4 Flash for high-frequency low-cost review, and Claude Code, Qoder and Cursor for writing. No matter how strong the model, work needs supervision — ideally from an independent third party.