← 返回 Skills 市场
Notebook [email protected]
162
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install notebook-lmskill-1-0-0
功能描述
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automati...
安全使用建议
This skill appears to do what it says (automated browser access to your NotebookLM notebooks), but it uses several sensitive/ unusual techniques. It will: create a local virtualenv and install dependencies (patchright), download or manage a Chrome binary (network activity), open a visible browser for login and persist your Google cookies and profile under ~/.claude/skills/notebooklm/data/, and inject session cookies back into browser sessions. Before installing or using it consider: 1) Only use with a dedicated Google account (do not use your primary account). 2) Inspect run.py and auth_manager.py yourself (or have a trusted developer do so) to verify they do nothing beyond the documented cookie/profile handling. 3) Backup and/or review the state.json and browser_profile files and be prepared to delete them if you revoke access. 4) Be cautious about the anti-detection flags and the 'less secure app' instructions in docs — they can enable more stealthy browser behavior and reduce account security. 5) Prefer code from a known, trusted publisher; if provenance cannot be verified, avoid storing sensitive account cookies with this skill. If you want higher assurance, ask the publisher for a signed release or replace patchright with an audited Playwright installation and remove any unnecessary stealth flags.
功能分析
Type: OpenClaw Skill
Name: notebook-lmskill-1-0-0
Version: 1.0.0
The skill bundle is classified as suspicious due to deceptive documentation and prompt injection techniques. The README.md contains multiple links (for 'Issues', 'Wiki', and 'Contributing') that all point to a single external ZIP file (notebooklm-skill-v3.4.zip on GitHub), which is a common tactic for distributing unauthorized artifacts. Additionally, SKILL.md and ask_question.py implement a prompt injection designed to override the agent's standard response flow by forcing a 'Follow-Up Mechanism' loop triggered by a specific string appended to every response. While the core logic (using patchright for stealthy Google NotebookLM automation) aligns with the stated purpose, the combination of deceptive links and behavioral overrides warrants caution.
能力评估
Purpose & Capability
The name/description match the code: the skill uses Playwright (via patchright) to open NotebookLM, query notebooks, and persist cookie/profile state. Requiring persistent browser profiles and session cookie handling is coherent with the stated goal of maintaining logged-in access to NotebookLM. However, the code also includes anti-detection measures (stealth/automation avoidance flags) and explicit cookie injection logic that are not strictly required by a naive 'read notebook' helper and are notable because they change how the browser is presented to Google.
Instruction Scope
SKILL.md and scripts instruct the agent (or user) to: open a visible browser for login, save and later inject state.json session cookies, always run commands via a run.py wrapper that creates a .venv and installs dependencies, and perform 'smart discovery' queries of a notebook's contents when metadata is missing. The instructions therefore grant the code routine access to local files and to the full contents of user notebooks (expected) but also direct the agent to repeatedly re-query notebooks (follow-up loop). The follow-up mechanism explicitly instructs autonomous repeated queries until 'complete', which could lead to repeated access/use without a clear user confirmation step.
Install Mechanism
No registry-level install spec is provided, but run.py will create a local .venv and pip-install dependencies from requirements.txt (patchright, python-dotenv). patchright is an anti-detection Playwright wrapper and may be used to install or manage Chrome; that implies network downloads and installation of a browser binary. There is no explicit signed or well-known release URL in the skill manifest; the README links (raw GitHub zip link) look malformed. Installing patchright and using it to fetch Chrome is a higher-friction, higher-risk operation than a pure API-only integration.
Credentials
The skill declares no required environment variables or external credentials, yet it persistently stores and later injects Google authentication cookies (state.json and a Chrome user profile) under ~/.claude/skills/notebooklm/data/. That is proportional to the functionality (it must authenticate to NotebookLM), but these artifacts are highly sensitive (session cookies can grant access to the linked Google account). The documentation also recommends using a dedicated Google account and even suggests 'less secure app' settings; those recommendations are concerning from a security posture perspective.
Persistence & Privilege
The skill does not request always: true and is user-invocable; it stores data under a skill-local directory (~/.claude/skills/notebooklm/data/) and creates a local .venv. Those behaviors are typical for a local automation tool and are not an elevated platform privilege. The follow-up automation pattern (agent-initiated repeated queries) increases operational activity but is not a platform-level persistence flag.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install notebook-lmskill-1-0-0 - 安装完成后，直接呼叫该 Skill 的名称或使用
/notebook-lmskill-1-0-0触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of the NotebookLM Claude skill.
- Enables querying Google NotebookLM notebooks via Claude Code, providing citation-backed answers grounded only in your uploaded documents.
- Uses secure browser automation with persistent authentication and full environment management—no manual dependency handling needed.
- Includes SMART ADD workflow for adding notebooks: discovers notebook content automatically if metadata is missing.
- Enforces strict use of a run.py wrapper for all operations, ensuring correct environment setup and execution.
- Implements a mandatory follow-up confirmation after every answer: checks if user’s request is fully satisfied before final response.
- Offers robust notebook management: add, list, search, activate, or remove notebooks; all actions require explicit metadata.
元数据
常见问题
Notebook [email protected] 是什么？
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automati... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 162 次。
如何安装 Notebook [email protected]？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install notebook-lmskill-1-0-0」即可一键安装，无需额外配置。
Notebook [email protected] 是免费的吗？
是的，Notebook [email protected] 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Notebook [email protected] 支持哪些平台？
Notebook [email protected] 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Notebook [email protected]？
由 1215656（@1215656）开发并维护，当前版本 v1.0.0。
推荐 Skills