Overview
- Skill Key
- antaripnandi/notebooklm-bypass
- Author
- antaripnandi
- Source Repo
- openclaw/skills
- Version
- -
- Source Path
- skills/antaripnandi/notebooklm-bypass
- Latest Commit SHA
- 9cb23015295ebc8487cce3f3fa0a58e221bfa46b
Programmatic NotebookLM control with auto-recovery for authentication errors.
Stars
0
Installs
0
Status
ACTIVE
Visibility
PUBLIC
直接复制以下提示词,发送给你的 AI 助手即可完成安装。
请先检查是否已安装 SkillHub 商店,若未安装,请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店,然后安装 notebooklm 技能。 若已安装,则直接安装 notebooklm 技能。
# NotebookLM CLI
## Commands
```bash
notebooklm list # List all notebooks + IDs
notebooklm create "Name" # Create notebook → returns ID
notebooklm source add "<url_or_file>" -n <ID> # Add URL/PDF/YouTube to notebook
notebooklm source add "<url>" -n <ID> --wait # Add + wait for processing
notebooklm source list -n <ID> # List sources in notebook
notebooklm ask "Question" -n <ID> # Query AI against sources
```
## Rules
1. **No playlists.** Extract individual YouTube URLs and add one by one.
2. **Max 50 sources** per notebook.
3. **Use `--wait`** when adding sources in scripts to ensure processing completes.
4. **Auth Recovery:** If `notebooklm` fails with "Authentication expired", you MUST ask the user for explicit permission before recovering. Propose running `python {WORKSPACE_DIR}/skills/notebooklm-bypass/scripts/auto_playwright.py`. If and only if they approve, run the script. This script steals fresh cookies and automatically injects them into your Windows Environment Variables. Once complete, retry your command.
# OpenClaw NotebookLM Stealth Auth Skill This is a custom drop-in skill for the [OpenClaw Framework](https://github.com/openclaw/openclaw) that permanently solves the "Authentication expired" login loop encountered when using the NotebookLM CLI. ## Background: The Multi-Day Auth Loop Nightmare For days, OpenClaw users have faced a critical bug: Google frequently rotates session cookies for security. When these cookies expire, the `notebooklm` CLI tool crashes with an `Authentication expired` error. Normally, this breaks headless AI agents completely. The agent fails its task, drops what it's doing, and the human user is forced to intervene, open their terminal, manually run `notebooklm login`, wait for the browser, and press Enter. If you tried to bypass it using the `NOTEBOOKLM_AUTH_JSON` environment variable, the Playwright CLI tool would often drop the cookies due to a `SameSite: Lax` cross-origin security bug. This skill fixes all of that by **giving your OpenClaw agent the ability to self-heal its own authentication.** --- ## Features - **One-Click Consent Recovery**: When OpenClaw gets an auth error, it asks your permission before running the included script to fetch fresh cookies, ensuring no silent credential harvesting occurs. - **Native Playwright Integration**: The script opens a visible browser window for 5 seconds to naturally bypass Google's "unsecure browser" bot detection. - **Windows Auto-Injection**: Automatically injects the refreshed cookies natively into the `NOTEBOOKLM_AUTH_JSON` persistent environment variable, bypassing the Playwright cross-origin security drop bug. --- ## The A-Z Setup Guide ### Step 2: The One-Time Interactive Login You must establish a persistent Chrome profile that is logged into your Google Account. 1. Open your terminal and run: ```bash notebooklm login ``` 2. A browser window will open. Log into your Google account. 3. Once you see the NotebookLM dashboard, go back to y...
heyixuan2
Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or any 3D printing task. Full pipeline: search → generate → analyze → colorize → preview → open BS → user slice → print → monitor. Supports all 9 Bambu Lab printers (A1 Mini, A1, P1S, P2S, X1C, X1E, H2C, H2S, H2D).
openstockdata
OpenClaw Skill for stock data analysis
capt-marbles
Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discoverability and citation.
camopel
Free multi-engine web search via ddgs CLI (DuckDuckGo, Google, Bing, Brave, Yandex, Yahoo, Wikipedia) + arXiv API search. No API keys required. Use when user needs web search, research paper discovery, or when other skills need a search backend. Drop-in replacement for web-search-plus.
camopel
Local arXiv paper manager with semantic search. Crawls arXiv categories, downloads PDFs, chunks content, and indexes with FAISS + Ollama embeddings. No cloud API keys required — everything runs locally.
camohiddendj
DuckDuckGo HTML search scraper CLI with JSON, CSV, OpenSearch, markdown, and compact outputs.