Agent Skill
Notebooklm skill
notebooklmteng-lin/notebooklm-pySKILL.md
Install, authenticate, troubleshoot, and operate Gemini Notebook through the notebooklm-py CLI or typed async Python API. Use for notebook and source management, grounded chat and research, and artifact generation or download when the user mentions Gemini Notebook, notebooklm-py, the notebooklm CLI, or its Python API. Do not use for the generic Gemini API or unrelated content creation.
always on
79 tokname + description
once used
3,746 tokSKILL.md body
bundled files
6564 scripts
repo stars
20kGitHub
Install the Notebooklm skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/teng-lin/notebooklm-py --skill notebooklm
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/teng-lin/notebooklm-py.git /tmp/notebooklm-py mkdir -p ~/.claude/skills cp -R /tmp/notebooklm-py ~/.claude/skills/notebooklm
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 79 tok |
| When the agent uses it | The SKILL.md instructions | 3,746 tok |
| Only if opened | 65 bundled files (1.0 MB) | varies |
Until it is used, notebooklm costs about 17× less than the median MCP server we measured (1,362 tokens on every turn). Skills vs MCP study
Checks
- Ships scripts the agent can run. Read them before installing.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Gemini Notebook Automation
- Setup and Authentication
- Operating Invariants
- Authorization Boundaries
- Command Discovery
- Canonical Source-to-Artifact Workflow
- Deep Research
- Python API Baseline
- Generation Notes
- Output and Citations
- Failure Handling
- Skill Installation