Skill：notebooklm py
Unofficial Python API and agentic skill for Google Gemini Notebook. Full programmatic access to NotebookLM's features—including capabilities the web UI doesn't expose—via Python, CLI, and AI agents like Claude Code, Codex, and OpenClaw.
适用场景
招聘人事
适合角色
介绍
以下内容整理自开源仓库 `teng-lin/notebooklm-py` 的 README / SKILL.md 摘要： --- name: notebooklm description: Operate Google Gemini Notebook through notebooklm-py to create notebooks, add sources, chat over content, run research, generate and download artifacts, and use features beyond the web UI. Use when the user names Google Gemini Notebook or asks to use it for podcasts, videos, reports, quizzes, flashcards, slide decks, infographics, mind maps, or source-grounded summaries. --- # Google Gemini Notebook Automation Use the `notebooklm` CLI for agent workflows. Prefer `--json` and explicit IDs so every operation is inspectable and safe under concurrency. Use the typed async Python API only when the user requests application code or the CLI cannot express the workflow. ## Setup and Authentication Install the package in the user's existing environment; do not create a separate environment unless requested: ```bash pip install "notebooklm-py[browser]" pip install "notebooklm-py[cookies]" # optional browser-cookie extraction ``` In a resettable headless sandbox that reuses a host-generated `storage_state.json` or `NOTEBOOKLM_AUTH_JSON`, the base `pip install notebooklm-py` is sufficient. Reusing a `master_token.json` requires `pip install "notebooklm-py[headless]"`; `[browser]` is needed for interactive login, and `[cookies]` is needed for browser-cookie extraction. Use PyPI or a release tag, not an unreleased `main` checkout. For the extras matrix, headless setup, CI secrets, skill installation, or the opt-in Android backend, read the [installation guide](https://github.com/teng-lin/notebooklm-py/blob/main/docs/installation.md). Before a workflow, verify real authentication rather than merely parsing the cookie file: ```bash notebooklm auth check --test --json ``` Require both `"status": "ok"` and `"checks.token_fetch": true`. If validation fails: - With a display, run `notebooklm login` and validate again. - In a headless environment, install `[cookies]` and use `notebooklm login --browser-cookies <browser>`. Use `notebooklm auth inspect --browser <browser>` first when account selection is unclear. - If previously valid cookies became stale, try `notebooklm auth refresh`; use `notebooklm auth refresh --browser-cookies <browser>` after signing back into the browser. `notebooklm status` reports selected-notebook context, not authentication. Treat `storage_state.json`, `master_token.json`, and `NOTEBOOKLM_AUTH_JSON` as bearer credentials: never print, log, or commit them. Prefer a secret store in CI. ## Operating Invariants 1. Use `--json` for discovery and mutations, then retain the returned full UUIDs. Important envelopes are `.notebook.id` from `create`, `.source.id` from `source add`, and `.task_id` from asynchronous generators. `generate mind-map` instead returns `mind_map`, `note_id`, and `kind --- **说明**：内容由公开仓库整理，使用前请自行核对是否适合你的场景。
安装方式
1. 打开仓库：https://github.com/teng-lin/notebooklm-py 2. 查找 SKILL.md 或 README 中的安装章节 3. 克隆或下载所需 Skill 子目录到本地 skills 路径（如 `.cursor/skills/` 或 `.claude/skills/`） 4. 重启 / 重载 Agent 客户端 5. 用一条真实任务验证 Skill 是否被正确加载
适用平台
- Claude
- Codex