[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75N0S6N0EHWDXH1V5KJ7AMJ":3,"skill-same:01M75N0S6N0EHWDXH1V5KJ7AMJ":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M75N0S6N0EHWDXH1V5KJ7AMJ","nblm",null,"Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.","javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmagicseek\u002Fnblm\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: nblm\ndescription: Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.\n---\n\n# NotebookLM Quick Commands\n\nQuery Google NotebookLM for source-grounded, citation-backed answers.\n\n## Environment\n\nAll dependencies and authentication are handled automatically by `run.py`:\n- First run creates `.venv` and installs Python\u002FNode.js dependencies\n- If Google auth is missing or expired, a browser window opens automatically\n- No manual pre-flight steps required\n\n---\n\n## Usage\n\n`\u002Fnblm \u003Ccommand> [args]`\n\n## Commands\n\n### Notebook Management\n| Command | Description |\n|---------|-------------|\n| `login` | Authenticate with Google |\n| `status` | Show auth and library status |\n| `accounts` | List all Google accounts |\n| `accounts add` | Add a new Google account |\n| `accounts switch \u003Cid>` | Switch active account (by index or email) |\n| `accounts remove \u003Cid>` | Remove an account |\n| `local` | List notebooks in local library |\n| `remote` | List all notebooks from NotebookLM API |\n| `create \u003Cname>` | Create a new notebook |\n| `delete [--id ID]` | Delete a notebook |\n| `rename \u003Cname> [--id ID]` | Rename a notebook |\n| `summary [--id ID]` | Get AI-generated summary |\n| `describe [--id ID]` | Get description and suggested topics |\n| `add \u003Curl-or-id>` | Add notebook to local library (auto-detects URL vs notebook ID) |\n| `activate \u003Cid>` | Set active notebook |\n\n### Source Management\n| Command | Description |\n|---------|-------------|\n| `sources [--id ID]` | List sources in notebook |\n| `upload \u003Cfile>` | Upload a single file |\n| `upload \u003Cfolder>` | Sync a folder of files to NotebookLM |\n| `upload-zlib \u003Curl>` | Download from Z-Library and upload |\n| `upload-url \u003Curl>` | Add URL as source |\n| `upload-youtube \u003Curl>` | Add YouTube video as source |\n| `upload-text \u003Ctitle> [--content TEXT]` | Add text as source |\n| `source-text \u003Csource-id>` | Get full indexed text |\n| `source-guide \u003Csource-id>` | Get AI summary and keywords |\n| `source-rename \u003Csource-id> \u003Cname>` | Rename a source |\n| `source-refresh \u003Csource-id>` | Re-fetch URL content |\n| `source-delete \u003Csource-id>` | Delete a source |\n\n**Upload options:**\n- `--use-active` - Upload to the currently active notebook\n- `--create-new` - Create a new notebook named after the file\u002Ffolder\n- `--notebook-id \u003Cid>` - Upload to a specific notebook\n- `--dry-run` - Show sync plan without executing (folder sync)\n- `--rebuild` - Force rebuild tracking file (folder sync)\n\n**Important:** When user runs upload without specifying a target, ASK them first:\n> \"Would you like to upload to the active notebook, or create a new notebook?\"\nThen pass the appropriate flag (`--use-active` or `--create-new`).\n\n### Chat & Audio\u002FMedia\n| Command | Description |\n|---------|-------------|\n| `ask \u003Cquestion>` | Query NotebookLM |\n| `podcast [--instructions TEXT]` | Generate audio podcast |\n| `podcast-status \u003Ctask-id>` | Check podcast generation status |\n| `podcast-download [output-path]` | Download latest podcast |\n| `briefing [--instructions TEXT]` | Generate brief audio summary |\n| `debate [--instructions TEXT]` | Generate debate-style audio |\n| `slides [--instructions TEXT]` | Generate slide deck |\n| `slides-download [output-path]` | Download slide deck as PDF |\n| `infographic [--instructions TEXT]` | Generate infographic |\n| `infographic-download [output-path]` | Download infographic |\n| `media-list [--type TYPE]` | List generated media (audio\u002Fvideo\u002Fslides\u002Finfographic) |\n| `media-delete \u003Cid>` | Delete a generated media item |\n\n## Command Routing\n\nBased on `$ARGUMENTS`, execute the appropriate command:\n\n$IF($ARGUMENTS,\n  Parse the command from: \"$ARGUMENTS\"\n\n  **login** → `python scripts\u002Frun.py auth_manager.py setup --service google`\n\n  **accounts** → `python scripts\u002Frun.py auth_manager.py accounts list`\n\n  **accounts add** → `python scripts\u002Frun.py auth_manager.py accounts add`\n\n  **accounts switch \u003Cid>** → `python scripts\u002Frun.py auth_manager.py accounts switch \"\u003Cid>\"`\n\n  **accounts remove \u003Cid>** → `python scripts\u002Frun.py auth_manager.py accounts remove \"\u003Cid>\"`\n\n  **status** → Run both:\n  - `python scripts\u002Frun.py auth_manager.py status`\n  - `python scripts\u002Frun.py notebook_manager.py list`\n\n  **local** → `python scripts\u002Frun.py notebook_manager.py list`\n\n  **remote** → `python scripts\u002Frun.py nblm_cli.py notebooks`\n\n  **create \u003Cname>** → `python scripts\u002Frun.py nblm_cli.py create \"\u003Cname>\"`\n\n  **delete [--id ID]** → `python scripts\u002Frun.py nblm_cli.py delete \u003Cargs>`\n\n  **rename \u003Cname> [--id ID]** → `python scripts\u002Frun.py nblm_cli.py rename \"\u003Cname>\" \u003Cargs>`\n\n  **summary [--id ID]** → `python scripts\u002Frun.py nblm_cli.py summary \u003Cargs>`\n\n  **describe [--id ID]** → `python scripts\u002Frun.py nblm_cli.py describe \u003Cargs>`\n\n  **add \u003Curl-or-id>** → Smart add workflow (auto-detects URL vs notebook ID)\n\n  **activate \u003Cid>** → `python scripts\u002Frun.py notebook_manager.py activate --id \"\u003Cid>\"`\n\n  **sources [--id ID]** → `python scripts\u002Frun.py nblm_cli.py sources \u003Cargs>`\n\n  **upload \u003Cfile>** → First ASK user: \"Upload to active notebook or create new?\" Then:\n    - Active: `python scripts\u002Frun.py source_manager.py add --file \"\u003Cfile>\" --use-active`\n    - New: `python scripts\u002Frun.py source_manager.py add --file \"\u003Cfile>\" --create-new`\n\n  **upload \u003Cfolder>** → Sync a folder:\n    - First ASK user: \"Sync to active notebook, create new, or specify notebook?\"\n    - Active: `python scripts\u002Frun.py source_manager.py sync \"\u003Cfolder>\" --use-active`\n    - New: `python scripts\u002Frun.py source_manager.py sync \"\u003Cfolder>\" --create-new`\n    - Specific: `python scripts\u002Frun.py source_manager.py sync \"\u003Cfolder>\" --notebook-id ID`\n    - Dry-run: `python scripts\u002Frun.py source_manager.py sync \"\u003Cfolder>\" --dry-run`\n    - Rebuild: `python scripts\u002Frun.py source_manager.py sync \"\u003Cfolder>\" --rebuild`\n\n  **upload-zlib \u003Curl>** → First ASK user: \"Upload to active notebook or create new?\" Then:\n    - Active: `python scripts\u002Frun.py source_manager.py add --url \"\u003Curl>\" --use-active`\n    - New: `python scripts\u002Frun.py source_manager.py add --url \"\u003Curl>\" --create-new`\n\n  **upload-url \u003Curl>** → `python scripts\u002Frun.py nblm_cli.py upload-url \"\u003Curl>\"`\n\n  **upload-youtube \u003Curl>** → `python scripts\u002Frun.py nblm_cli.py upload-youtube \"\u003Curl>\"`\n\n  **upload-text \u003Ctitle>** → `python scripts\u002Frun.py nblm_cli.py upload-text \"\u003Ctitle>\" \u003Cargs>`\n\n  **source-text \u003Cid>** → `python scripts\u002Frun.py nblm_cli.py source-text \"\u003Cid>\"`\n\n  **source-guide \u003Cid>** → `python scripts\u002Frun.py nblm_cli.py source-guide \"\u003Cid>\"`\n\n  **source-rename \u003Cid> \u003Cname>** → `python scripts\u002Frun.py nblm_cli.py source-rename \"\u003Cid>\" \"\u003Cname>\"`\n\n  **source-refresh \u003Cid>** → `python scripts\u002Frun.py nblm_cli.py source-refresh \"\u003Cid>\"`\n\n  **source-delete \u003Cid>** → `python scripts\u002Frun.py nblm_cli.py source-delete \"\u003Cid>\"`\n\n  **ask \u003Cquestion>** → `python scripts\u002Frun.py nblm_cli.py ask \"\u003Cquestion>\"`\n\n  **podcast** → `python scripts\u002Frun.py artifact_manager.py generate --format DEEP_DIVE \u003Cargs>`\n\n  **podcast-status \u003Ctask-id>** → `python scripts\u002Frun.py artifact_manager.py status --task-id \"\u003Ctask-id>\"`\n\n  **podcast-download [output-path]** → `python scripts\u002Frun.py artifact_manager.py download \"\u003Coutput-path>\"`\n\n  **briefing** → `python scripts\u002Frun.py artifact_manager.py generate --format BRIEF \u003Cargs>`\n\n  **debate** → `python scripts\u002Frun.py artifact_manager.py generate --format DEBATE \u003Cargs>`\n\n  **slides** → `python scripts\u002Frun.py artifact_manager.py generate-slides \u003Cargs>`\n\n  **slides-download [output-path]** → `python scripts\u002Frun.py artifact_manager.py download \"\u003Coutput-path>\" --type slide-deck`\n\n  **infographic** → `python scripts\u002Frun.py artifact_manager.py generate-infographic \u003Cargs>`\n\n  **infographic-download [output-path]** → `python scripts\u002Frun.py artifact_manager.py download \"\u003Coutput-path>\" --type infographic`\n\n  **media-list [--type TYPE]** → `python scripts\u002Frun.py artifact_manager.py list \u003Cargs>`\n\n  **media-delete \u003Cid>** → `python scripts\u002Frun.py artifact_manager.py delete \"\u003Cid>\"`\n\n  If command not recognized, show usage help.,\n\n  Show available commands with `\u002Fnblm` (no arguments)\n)\n\n## Podcast Options\n\n```\n\u002Fnblm podcast --length DEFAULT --wait --output .\u002Fpodcast.mp3\n\u002Fnblm podcast --instructions \"Focus on the key findings\"\n\u002Fnblm briefing --wait --output .\u002Fsummary.mp3\n\u002Fnblm debate --instructions \"Compare the two approaches\"\n```\n\n| Option | Values |\n|--------|--------|\n| `--length` | `SHORT`, `DEFAULT`, `LONG` |\n| `--instructions` | Custom instructions for the content |\n| `--wait` | Wait for generation to complete |\n| `--output` | Download path (requires `--wait`) |\n\n## Slide Deck Options\n\n```\n\u002Fnblm slides --format DETAILED_DECK --wait --output .\u002Fpresentation.pdf\n\u002Fnblm slides --instructions \"Focus on key diagrams\" --format PRESENTER_SLIDES\n```\n\n| Option | Values |\n|--------|--------|\n| `--format` | `DETAILED_DECK`, `PRESENTER_SLIDES` |\n| `--length` | `SHORT`, `DEFAULT` |\n| `--instructions` | Custom instructions for the content |\n| `--wait` | Wait for generation to complete |\n| `--output` | Download path (requires `--wait`) |\n\n## Infographic Options\n\n```\n\u002Fnblm infographic --orientation LANDSCAPE --wait --output .\u002Fvisual.png\n\u002Fnblm infographic --instructions \"Highlight comparison\" --detail-level DETAILED\n```\n\n| Option | Values |\n|--------|--------|\n| `--orientation` | `LANDSCAPE`, `PORTRAIT`, `SQUARE` |\n| `--detail-level` | `CONCISE`, `STANDARD`, `DETAILED` |\n| `--instructions` | Custom instructions for the content |\n| `--wait` | Wait for generation to complete |\n| `--output` | Download path (requires `--wait`) |\n\n## Media Generation\n\n| Command | Description | Output |\n|---------|-------------|--------|\n| `\u002Fnblm podcast` | Deep-dive audio discussion | MP3 |\n| `\u002Fnblm briefing` | Brief audio summary | MP3 |\n| `\u002Fnblm debate` | Debate-style audio | MP3 |\n| `\u002Fnblm slides` | Slide deck presentation | PDF |\n| `\u002Fnblm infographic` | Visual infographic | PNG |\n\n### Examples\n```\n\u002Fnblm podcast --wait --output .\u002Fdeep-dive.mp3\n\u002Fnblm briefing --instructions \"Focus on chapter 3\" --wait\n\u002Fnblm debate --length LONG --wait --output .\u002Fdebate.mp3\n\u002Fnblm slides --instructions \"Include key diagrams\" --format DETAILED_DECK --wait --output .\u002Fpresentation.pdf\n\u002Fnblm infographic --orientation LANDSCAPE --detail-level DETAILED --wait --output .\u002Fsummary.png\n```\n\n### Download & Manage\n```\n\u002Fnblm podcast-download .\u002Fmy-podcast.mp3\n\u002Fnblm slides-download .\u002Fpresentation.pdf\n\u002Fnblm infographic-download .\u002Fvisual.png\n\u002Fnblm media-list                     # List all generated media\n\u002Fnblm media-list --type audio        # List only audio\n\u002Fnblm media-delete \u003Cid>              # Delete a media item\n```\n\n---\n\n# Extended Documentation\n\n## When to Use This Skill\n\nTrigger when user:\n- Mentions NotebookLM explicitly\n- Shares NotebookLM URL (`https:\u002F\u002Fnotebooklm.google.com\u002Fnotebook\u002F...`)\n- Asks to query their notebooks\u002Fdocumentation\n- Wants to add documentation to NotebookLM library\n- Uses phrases like \"ask my NotebookLM\", \"check my docs\", \"query my notebook\"\n\n## ⚠️ CRITICAL: Add Command - Smart Discovery\n\nThe add command now **automatically discovers metadata** from the notebook:\n\n```bash\n# Smart Add (auto-discovers name, description, topics)\npython scripts\u002Frun.py notebook_manager.py add \u003Cnotebook-id-or-url>\n\n# With optional overrides\npython scripts\u002Frun.py notebook_manager.py add \u003Cid> --name \"Custom Name\" --topics \"custom,topics\"\n```\n\n**What Smart Add does:**\n1. Fetches notebook title from NotebookLM API\n2. Queries the notebook content to generate description and topics\n3. Adds to local library with discovered metadata\n\n**Supported input formats:**\n- Notebook ID: `5fd9f36b-8000-401d-a7a0-7aa3f7832644`\n- Full URL: `https:\u002F\u002Fnotebooklm.google.com\u002Fnotebook\u002F5fd9f36b-8000-401d-a7a0-7aa3f7832644`\n\nNEVER manually specify `--name`, `--description`, or `--topics` unless the user explicitly provides them.\n\n## Critical: Always Use run.py Wrapper\n\n**NEVER call scripts directly. ALWAYS use `python scripts\u002Frun.py [script]`:**\n\n```bash\n# ✅ CORRECT - Always use run.py:\npython scripts\u002Frun.py auth_manager.py status\npython scripts\u002Frun.py notebook_manager.py list\npython scripts\u002Frun.py ask_question.py --question \"...\"\n\n# ❌ WRONG - Never call directly:\npython scripts\u002Fauth_manager.py status  # Fails without venv!\n```\n\nThe `run.py` wrapper automatically:\n1. Creates `.venv` if needed\n2. Installs all dependencies\n3. Activates environment\n4. Executes script properly\n\n## Core Workflow\n\n### Step 1: Check Authentication Status\n```bash\npython scripts\u002Frun.py auth_manager.py status\n```\n\nIf not authenticated, proceed to setup.\n\n### Step 2: Authenticate (One-Time Setup)\n```bash\n# Browser MUST be visible for manual Google login\npython scripts\u002Frun.py auth_manager.py setup\n```\n\n**Important:**\n- Browser is VISIBLE for authentication\n- Browser window opens automatically\n- User must manually log in to Google\n- Tell user: \"A browser window will open for Google login\"\n\n### Step 3: Manage Notebook Library\n\n```bash\n# List all notebooks\npython scripts\u002Frun.py notebook_manager.py list\n\n# BEFORE ADDING: Ask user for metadata if unknown!\n# \"What does this notebook contain?\"\n# \"What topics should I tag it with?\"\n\n# Add notebook to library (ALL parameters are REQUIRED!)\npython scripts\u002Frun.py notebook_manager.py add \\\n  --url \"https:\u002F\u002Fnotebooklm.google.com\u002Fnotebook\u002F...\" \\\n  --name \"Descriptive Name\" \\\n  --description \"What this notebook contains\" \\  # REQUIRED - ASK USER IF UNKNOWN!\n  --topics \"topic1,topic2,topic3\"  # REQUIRED - ASK USER IF UNKNOWN!\n\n# Search notebooks by topic\npython scripts\u002Frun.py notebook_manager.py search --query \"keyword\"\n\n# Set active notebook\npython scripts\u002Frun.py notebook_manager.py activate --id notebook-id\n\n# Remove notebook\npython scripts\u002Frun.py notebook_manager.py remove --id notebook-id\n```\n\n### Quick Workflow\n1. Check library: `python scripts\u002Frun.py notebook_manager.py list`\n2. Ask question: `python scripts\u002Frun.py ask_question.py --question \"...\" --notebook-id ID`\n\n### Step 4: Ask Questions\n\n```bash\n# Basic query (uses active notebook if set)\npython scripts\u002Frun.py ask_question.py --question \"Your question here\"\n\n# Query specific notebook\npython scripts\u002Frun.py ask_question.py --question \"...\" --notebook-id notebook-id\n\n# Query with notebook URL directly\npython scripts\u002Frun.py ask_question.py --question \"...\" --notebook-url \"https:\u002F\u002F...\"\n\n# Show browser for debugging\npython scripts\u002Frun.py ask_question.py --question \"...\" --show-browser\n```\n\n## Follow-Up Mechanism (CRITICAL)\n\nEvery NotebookLM answer ends with: **\"EXTREMELY IMPORTANT: Is that ALL you need to know?\"**\n\n**Required Claude Behavior:**\n1. **STOP** - Do not immediately respond to user\n2. **ANALYZE** - Compare answer to user's original request\n3. **IDENTIFY GAPS** - Determine if more information needed\n4. **ASK FOLLOW-UP** - If gaps exist, immediately ask:\n   ```bash\n   python scripts\u002Frun.py ask_question.py --question \"Follow-up with context...\"\n   ```\n5. **REPEAT** - Continue until information is complete\n6. **SYNTHESIZE** - Combine all answers before responding to user\n\n## Z-Library Integration\n\n### Triggers\n- User provides Z-Library URL (zlib.li, z-lib.org, zh.zlib.li)\n- User says \"download this book to NotebookLM\"\n- User says \"add this book from Z-Library\"\n\n### Setup (One-Time)\n```bash\n# Authenticate with Z-Library\npython scripts\u002Frun.py auth_manager.py setup --service zlibrary\n```\n\n### Commands\n```bash\n# Add book from Z-Library\npython scripts\u002Frun.py source_manager.py add --url \"https:\u002F\u002Fzh.zlib.li\u002Fbook\u002F...\"\n\n# Check Z-Library auth status\npython scripts\u002Frun.py auth_manager.py status --service zlibrary\n```\n\n## Script Reference\n\n### Authentication Management (`auth_manager.py`)\n```bash\npython scripts\u002Frun.py auth_manager.py setup                    # Default: Google\npython scripts\u002Frun.py auth_manager.py setup --service google\npython scripts\u002Frun.py auth_manager.py setup --service zlibrary\npython scripts\u002Frun.py auth_manager.py status                   # Show all services\npython scripts\u002Frun.py auth_manager.py status --service zlibrary\npython scripts\u002Frun.py auth_manager.py clear --service zlibrary # Clear auth\n\n# Multi-Account Management (Google)\npython scripts\u002Frun.py auth_manager.py accounts list             # List all accounts\npython scripts\u002Frun.py auth_manager.py accounts add              # Add new account\npython scripts\u002Frun.py auth_manager.py accounts switch 1         # Switch by index\npython scripts\u002Frun.py auth_manager.py accounts switch user@gmail.com  # Switch by email\npython scripts\u002Frun.py auth_manager.py accounts remove 2         # Remove account\n```\n\n### Notebook Management (`notebook_manager.py`)\n```bash\npython scripts\u002Frun.py notebook_manager.py add --url URL --name NAME --description DESC --topics TOPICS\n# OR use notebook ID directly:\npython scripts\u002Frun.py notebook_manager.py add --notebook-id ID --name NAME --description DESC --topics TOPICS\npython scripts\u002Frun.py notebook_manager.py list\npython scripts\u002Frun.py notebook_manager.py search --query QUERY\npython scripts\u002Frun.py notebook_manager.py activate --id ID\npython scripts\u002Frun.py notebook_manager.py remove --id ID\npython scripts\u002Frun.py notebook_manager.py stats\n```\n\n### Question Interface (`ask_question.py`)\n```bash\npython scripts\u002Frun.py ask_question.py --question \"...\" [--notebook-id ID] [--notebook-url URL] [--show-browser]\n```\n\n### Source Manager (`source_manager.py`)\n```bash\n# Upload to active notebook\npython scripts\u002Frun.py source_manager.py add --file \"\u002Fpath\u002Fto\u002Fbook.pdf\" --use-active\n\n# Create new notebook for upload\npython scripts\u002Frun.py source_manager.py add --file \"\u002Fpath\u002Fto\u002Fbook.pdf\" --create-new\n\n# Upload to specific notebook\npython scripts\u002Frun.py source_manager.py add --file \"\u002Fpath\u002Fto\u002Fbook.pdf\" --notebook-id NOTEBOOK_ID\n\n# Z-Library download and upload\npython scripts\u002Frun.py source_manager.py add --url \"https:\u002F\u002Fzh.zlib.li\u002Fbook\u002F...\" --use-active\npython scripts\u002Frun.py source_manager.py add --url \"https:\u002F\u002Fzh.zlib.li\u002Fbook\u002F...\" --create-new\n\n# Sync a folder (new!)\npython scripts\u002Frun.py source_manager.py sync \"\u002Fpath\u002Fto\u002Fdocs\" --use-active\npython scripts\u002Frun.py source_manager.py sync \"\u002Fpath\u002Fto\u002Fdocs\" --create-new\npython scripts\u002Frun.py source_manager.py sync \"\u002Fpath\u002Fto\u002Fdocs\" --notebook-id NOTEBOOK_ID\n\n# Sync options (new!)\npython scripts\u002Frun.py source_manager.py sync \"\u002Fpath\u002Fto\u002Fdocs\" --dry-run    # Preview only\npython scripts\u002Frun.py source_manager.py sync \"\u002Fpath\u002Fto\u002Fdocs\" --rebuild   # Force re-hash all files\n```\n\n**Folder Sync:**\n- Scans folder for supported types: PDF, TXT, MD, DOCX, HTML, EPUB\n- Tracks sync state internally (no per-folder tracking file to manage)\n- Sync strategy: add new, update modified (delete + re-upload), skip unchanged\n- Multi-account aware (tracks which Google account was used)\n**Note:** One of `--use-active`, `--create-new`, or `--notebook-id` is REQUIRED.\nUploads wait for NotebookLM processing and print progress as `Ready: N\u002FT`. Press Ctrl+C to stop waiting.\nLocal file uploads use browser automation and require Google authentication.\nIf browser automation is unavailable, set `NOTEBOOKLM_UPLOAD_MODE=text` to upload extracted text instead (PDFs require `pypdf`).\n\n### Data Cleanup (`cleanup_manager.py`)\n```bash\npython scripts\u002Frun.py cleanup_manager.py                    # Preview cleanup\npython scripts\u002Frun.py cleanup_manager.py --confirm          # Execute cleanup\npython scripts\u002Frun.py cleanup_manager.py --preserve-library # Keep notebooks\n```\n\n### Watchdog Status (`auth_manager.py`)\n```bash\npython scripts\u002Frun.py auth_manager.py watchdog-status\n```\n\n## Environment Management\n\nThe virtual environment is automatically managed:\n- First run creates `.venv` automatically\n- Dependencies install automatically\n- Node.js dependencies install automatically\n- agent-browser daemon starts on demand and keeps browser state in memory\n- daemon stops after 10 minutes of inactivity (any agent-browser command resets the timer)\n- set `AGENT_BROWSER_OWNER_PID` to auto-stop when the agent process exits\n- `scripts\u002Frun.py` sets `AGENT_BROWSER_OWNER_PID` to its parent PID by default\n- Everything isolated in skill directory\n\nManual setup (only if automatic fails):\n```bash\npython -m venv .venv\nsource .venv\u002Fbin\u002Factivate  # Linux\u002FMac\npip install -r requirements.txt\nnpm install\nnpm run install-browsers\n```\n\n## Data Storage\n\nAll data stored in `~\u002F.claude\u002Fskills\u002Fnotebooklm\u002Fdata\u002F`:\n- `library.json` - Notebook metadata (with account associations)\n- `auth\u002Fgoogle\u002F` - Multi-account Google auth\n  - `index.json` - Account index (active account, list)\n  - `\u003Cn>-\u003Cemail>.json` - Per-account credentials\n- `auth\u002Fzlibrary.json` - Z-Library auth state\n- `agent_browser\u002Fsession_id` - Current daemon session ID\n- `agent_browser\u002Flast_activity.json` - Last activity timestamp for idle shutdown\n- `agent_browser\u002Fwatchdog.pid` - Idle watchdog process ID\n\n**Security:** Protected by `.gitignore`, never commit to git.\n\n## Configuration\n\nOptional `.env` file in skill directory:\n```env\nHEADLESS=false           # Browser visibility\nSHOW_BROWSER=false       # Default browser display\nSTEALTH_ENABLED=true     # Human-like behavior\nTYPING_WPM_MIN=160       # Typing speed\nTYPING_WPM_MAX=240\nDEFAULT_NOTEBOOK_ID=     # Default notebook\n```\n\n## Decision Flow\n\n```\nUser mentions NotebookLM\n    ↓\nCheck auth → python scripts\u002Frun.py auth_manager.py status\n    ↓\nIf not authenticated → python scripts\u002Frun.py auth_manager.py setup\n    ↓\nCheck\u002FAdd notebook → python scripts\u002Frun.py notebook_manager.py list\u002Fadd (with --description)\n    ↓\nActivate notebook → python scripts\u002Frun.py notebook_manager.py activate --id ID\n    ↓\nAsk question → python scripts\u002Frun.py ask_question.py --question \"...\"\n    ↓\nSee \"Is that ALL you need?\" → Ask follow-ups until complete\n    ↓\nSynthesize and respond to user\n```\n\n## Troubleshooting\n\n| Problem | Solution |\n|---------|----------|\n| ModuleNotFoundError | Use `run.py` wrapper |\n| Authentication fails | Browser must be visible for setup! --show-browser |\n| DAEMON_UNAVAILABLE | Ensure Node.js\u002Fnpm installed, run `npm install`, retry |\n| AUTH_REQUIRED | Run `python scripts\u002Frun.py auth_manager.py setup` |\n| ELEMENT_NOT_FOUND | Verify notebook URL and re-run with fresh page load |\n| Rate limit (50\u002Fday) | Wait or add another Google account with `accounts add` |\n| Browser crashes | `python scripts\u002Frun.py cleanup_manager.py --preserve-library` |\n| Notebook not found | Check with `notebook_manager.py list` |\n\n## Best Practices\n\n1. **Always use run.py** - Handles environment automatically\n2. **Check auth first** - Before any operations\n3. **Follow-up questions** - Don't stop at first answer\n4. **Browser visible for auth** - Required for manual login\n5. **Include context** - Each question is independent\n6. **Synthesize answers** - Combine multiple responses\n\n## Limitations\n\n- No session persistence (each question = new browser)\n- Rate limits on free Google accounts (50 queries\u002Fday per account; use multiple accounts to increase)\n- Manual upload required (user must add docs to NotebookLM)\n- Browser overhead (few seconds per question)\n\n## Resources (Skill Structure)\n\n**Important directories and files:**\n\n- `scripts\u002F` - All automation scripts (ask_question.py, notebook_manager.py, etc.)\n- `data\u002F` - Local storage for authentication and notebook library\n- `references\u002F` - Extended documentation:\n  - `api_reference.md` - Detailed API documentation for all scripts\n  - `troubleshooting.md` - Common issues and solutions\n  - `usage_patterns.md` - Best practices and workflow examples\n- `.venv\u002F` - Isolated Python environment (auto-created on first run)\n- `.gitignore` - Protects sensitive data from being committed\n","# NotebookLM Quick Commands\n\nQuery Google NotebookLM for source-grounded, citation-backed answers.\n\n## Environment\n\nAll dependencies and authentication are handled automatically by `run.py`:\n- First run creates `.venv` and installs Python\u002FNode.js dependencies\n- If Google auth is missing or expired, a browser window opens automatically\n- No manual pre-flight steps required\n\n---\n\n## Usage\n\n`\u002Fnblm \u003Ccommand> [args]`\n\n## Commands\n\n### Notebook Management\n| Command | Description |\n|---------|-------------|\n| `login` | Authenticate with Google |\n| `status` | Show auth and library status |\n| `accounts` | List all Google accounts |\n| `accounts add` | Add a new Google account |\n| `accounts switch \u003Cid>` | Switch active account (by index or email) |\n| `accounts remove \u003Cid>` | Remove an account |\n| `local` | List notebooks in local library |\n| `remote` | List all notebooks from NotebookLM API |\n| `create \u003Cname>` | Create a new notebook |\n| `delete [--id ID]` | Delete a notebook |\n| `rename \u003Cname> [--id ID]` | Rename a notebook |\n| `summary [--id ID]` | Get AI-generated summary |\n| `describe [--id ID]` | Get description and suggested topics |\n| `add \u003Curl-or-id>` | Add notebook to local library (auto-detects URL vs notebook ID) |\n| `activate \u003Cid>` | Set active notebook |\n\n### Source Management\n| Command | Description |\n|---------|-------------|\n| `sources [--id ID]` | List sources in notebook |\n| `upload \u003Cfile>` | Upload a single file |\n| `upload \u003Cfolder>` | Sync a folder of files to NotebookLM |\n| `upload-zlib \u003Curl>` | Download from Z-Library and upload |\n| `upload-url \u003Curl>` | Add URL as source |\n| `upload-youtube \u003Curl>` | Add YouTube video as source |\n| `upload-text \u003Ctitle> [--content TEXT]` | Add text as source |\n| `source-text \u003Csource-id>` | Get full indexed text |\n| `source-guide \u003Csource-id>` | Get AI summary and keywords |\n| `source-rename \u003Csource-id> \u003Cname>` | Rename a source |\n| `source-refresh \u003Csource-id>` | Re-fetch URL content |\n| `source-delete \u003Csource-id>` | Delete a source |\n\n**Upload options:**\n- `--use-active` - Upload to the currently active notebook\n- `--create-new` - Create a new notebook named after the file\u002Ffolder\n- `--notebook-id \u003Cid>` - Upload to a specific notebook\n- `--dry-run` - Show sync plan without executing (folder sync)\n- `--rebuild` - Force rebuild tracking file (folder sync)\n\n**Important:** When user runs upload without specifying a target, ASK them first:\n> \"Would you like to upload to the active notebook, or create a new notebook?\"\nThen pass the appropriate flag (`--use-active` or `--create-new`).\n\n### Chat & Audio\u002FMedia\n| Command | Description |\n|---------|-------------|\n| `ask \u003Cquestion>` | Query NotebookLM |\n| `podcast [--instructions TEXT]` | Generate audio podcast |\n| `podcast-status \u003Ctask-id>` | Check podcast generation status |\n| `podcast-download [output-path]` | Download latest podcast |\n| `briefing [--instructions TEXT]` | Generate brief audio summary |\n| `debate [--instructions TEXT]` | Generate debate-style audio |\n| `slides [--instructions TEXT]` | Generate slide deck |\n| `slides-download [output-path]` | Download slide deck as PDF |\n| `infographic [--instructions TEXT]` | Generate infographic |\n| `infographic-download [output-path]` | Download infographic |\n| `media-list [--type TYPE]` | List generated media (audio\u002Fvideo\u002Fslides\u002Finfographic) |\n| `media-delete \u003Cid>` | Delete a generated media item |\n\n## Command Routing\n\nBased on `$ARGUMENTS`, execute the appropriate command:\n\n$IF($ARGUMENTS,\n  Parse the command from: \"$ARGUMENTS\"\n\n  **login** → `python scripts\u002Frun.py auth_manager.py setup --service google`\n\n  **accounts** → `python scripts\u002Frun.py auth_manager.py accounts list`\n\n  **accounts add** → `python scripts\u002Frun.py auth_manager.py accounts add`\n\n  **accounts switch \u003Cid>** → `python scripts\u002Frun.py auth_manager.py accounts switch \"\u003Cid>\"`\n\n  **accounts remove \u003Cid>** → `python scripts\u002Frun.py auth_manager.py accounts remove \"\u003Cid>\"`\n\n  **status** → Run both:\n  - `python scripts\u002Frun.py auth_manager.py status`\n  - `python scripts\u002Frun.py notebook_manager.py list`\n\n  **local** → `python scripts\u002Frun.py notebook_manager.py list`\n\n  **remote** → `python scripts\u002Frun.py nblm_cli.py notebooks`\n\n  **create \u003Cname>** → `python scripts\u002Frun.py nblm_cli.py create \"\u003Cname>\"`\n\n  **delete [--id ID]** → `python scripts\u002Frun.py nblm_cli.py delete \u003Cargs>`\n\n  **rename \u003Cname> [--id ID]** → `python scripts\u002Frun.py nblm_cli.py rename \"\u003Cname>\" \u003Cargs>`\n\n  **summary [--id ID]** → `python scripts\u002Frun.py nblm_cli.py summary \u003Cargs>`\n\n  **describe [--id ID]** → `python scripts\u002Frun.py nblm_cli.py describe \u003Cargs>`\n\n  **add \u003Curl-or-id>** → Smart add workflow (auto-detects URL vs notebook ID)\n\n  **activate \u003Cid>** → `python scripts\u002Frun.py notebook_manager.py activate --id \"\u003Cid>\"`\n\n  **sources [--id ID]** → `python scripts\u002Frun.py nblm_cli.py sources \u003Cargs>`\n\n  **upload \u003Cfile>** → First ASK user: \"Upload to active notebook or create new?\" Then:\n    - Active: `python scripts\u002Frun.py source_manager.py add --file \"\u003Cfile>\" --use-active`\n    - New: `python scripts\u002Frun.py source_manager.py add --file \"\u003Cfile>\" --create-new`\n\n  **upload \u003Cfolder>** → Sync a folder:\n    - First ASK user: \"Sync to active notebook, create new, or specify notebook?\"\n    - Active: `python scripts\u002Frun.py source_manager.py sync \"\u003Cfolder>\" --use-active`\n    - New: `python scripts\u002Frun.py source_manager.py sync \"\u003Cfolder>\" --create-new`\n    - Specific: `python scripts\u002Frun.py source_manager.py sync \"\u003Cfolder>\" --notebook-id ID`\n    - Dry-run: `python scripts\u002Frun.py source_manager.py sync \"\u003Cfolder>\" --dry-run`\n    - Rebuild: `python scripts\u002Frun.py source_manager.py sync \"\u003Cfolder>\" --rebuild`\n\n  **upload-zlib \u003Curl>** → First ASK user: \"Upload to active notebook or create new?\" Then:\n    - Active: `python scripts\u002Frun.py source_manager.py add --url \"\u003Curl>\" --use-active`\n    - New: `python scripts\u002Frun.py source_manager.py add --url \"\u003Curl>\" --create-new`\n\n  **upload-url \u003Curl>** → `python scripts\u002Frun.py nblm_cli.py upload-url \"\u003Curl>\"`\n\n  **upload-youtube \u003Curl>** → `python scripts\u002Frun.py nblm_cli.py upload-youtube \"\u003Curl>\"`\n\n  **upload-text \u003Ctitle>** → `python scripts\u002Frun.py nblm_cli.py upload-text \"\u003Ctitle>\" \u003Cargs>`\n\n  **source-text \u003Cid>** → `python scripts\u002Frun.py nblm_cli.py source-text \"\u003Cid>\"`\n\n  **source-guide \u003Cid>** → `python scripts\u002Frun.py nblm_cli.py source-guide \"\u003Cid>\"`\n\n  **source-rename \u003Cid> \u003Cname>** → `python scripts\u002Frun.py nblm_cli.py source-rename \"\u003Cid>\" \"\u003Cname>\"`\n\n  **source-refresh \u003Cid>** → `python scripts\u002Frun.py nblm_cli.py source-refresh \"\u003Cid>\"`\n\n  **source-delete \u003Cid>** → `python scripts\u002Frun.py nblm_cli.py source-delete \"\u003Cid>\"`\n\n  **ask \u003Cquestion>** → `python scripts\u002Frun.py nblm_cli.py ask \"\u003Cquestion>\"`\n\n  **podcast** → `python scripts\u002Frun.py artifact_manager.py generate --format DEEP_DIVE \u003Cargs>`\n\n  **podcast-status \u003Ctask-id>** → `python scripts\u002Frun.py artifact_manager.py status --task-id \"\u003Ctask-id>\"`\n\n  **podcast-download [output-path]** → `python scripts\u002Frun.py artifact_manager.py download \"\u003Coutput-path>\"`\n\n  **briefing** → `python scripts\u002Frun.py artifact_manager.py generate --format BRIEF \u003Cargs>`\n\n  **debate** → `python scripts\u002Frun.py artifact_manager.py generate --format DEBATE \u003Cargs>`\n\n  **slides** → `python scripts\u002Frun.py artifact_manager.py generate-slides \u003Cargs>`\n\n  **slides-download [output-path]** → `python scripts\u002Frun.py artifact_manager.py download \"\u003Coutput-path>\" --type slide-deck`\n\n  **infographic** → `python scripts\u002Frun.py artifact_manager.py generate-infographic \u003Cargs>`\n\n  **infographic-download [output-path]** → `python scripts\u002Frun.py artifact_manager.py download \"\u003Coutput-path>\" --type infographic`\n\n  **media-list [--type TYPE]** → `python scripts\u002Frun.py artifact_manager.py list \u003Cargs>`\n\n  **media-delete \u003Cid>** → `python scripts\u002Frun.py artifact_manager.py delete \"\u003Cid>\"`\n\n  If command not recognized, show usage help.,\n\n  Show available commands with `\u002Fnblm` (no arguments)\n)\n\n## Podcast Options\n\n```\n\u002Fnblm podcast --length DEFAULT --wait --output .\u002Fpodcast.mp3\n\u002Fnblm podcast --instructions \"Focus on the key findings\"\n\u002Fnblm briefing --wait --output .\u002Fsummary.mp3\n\u002Fnblm debate --instructions \"Compare the two approaches\"\n```\n\n| Option | Values |\n|--------|--------|\n| `--length` | `SHORT`, `DEFAULT`, `LONG` |\n| `--instructions` | Custom instructions for the content |\n| `--wait` | Wait for generation to complete |\n| `--output` | Download path (requires `--wait`) |\n\n## Slide Deck Options\n\n```\n\u002Fnblm slides --format DETAILED_DECK --wait --output .\u002Fpresentation.pdf\n\u002Fnblm slides --instructions \"Focus on key diagrams\" --format PRESENTER_SLIDES\n```\n\n| Option | Values |\n|--------|--------|\n| `--format` | `DETAILED_DECK`, `PRESENTER_SLIDES` |\n| `--length` | `SHORT`, `DEFAULT` |\n| `--instructions` | Custom instructions for the content |\n| `--wait` | Wait for generation to complete |\n| `--output` | Download path (requires `--wait`) |\n\n## Infographic Options\n\n```\n\u002Fnblm infographic --orientation LANDSCAPE --wait --output .\u002Fvisual.png\n\u002Fnblm infographic --instructions \"Highlight comparison\" --detail-level DETAILED\n```\n\n| Option | Values |\n|--------|--------|\n| `--orientation` | `LANDSCAPE`, `PORTRAIT`, `SQUARE` |\n| `--detail-level` | `CONCISE`, `STANDARD`, `DETAILED` |\n| `--instructions` | Custom instructions for the content |\n| `--wait` | Wait for generation to complete |\n| `--output` | Download path (requires `--wait`) |\n\n## Media Generation\n\n| Command | Description | Output |\n|---------|-------------|--------|\n| `\u002Fnblm podcast` | Deep-dive audio discussion | MP3 |\n| `\u002Fnblm briefing` | Brief audio summary | MP3 |\n| `\u002Fnblm debate` | Debate-style audio | MP3 |\n| `\u002Fnblm slides` | Slide deck presentation | PDF |\n| `\u002Fnblm infographic` | Visual infographic | PNG |\n\n### Examples\n```\n\u002Fnblm podcast --wait --output .\u002Fdeep-dive.mp3\n\u002Fnblm briefing --instructions \"Focus on chapter 3\" --wait\n\u002Fnblm debate --length LONG --wait --output .\u002Fdebate.mp3\n\u002Fnblm slides --instructions \"Include key diagrams\" --format DETAILED_DECK --wait --output .\u002Fpresentation.pdf\n\u002Fnblm infographic --orientation LANDSCAPE --detail-level DETAILED --wait --output .\u002Fsummary.png\n```\n\n### Download & Manage\n```\n\u002Fnblm podcast-download .\u002Fmy-podcast.mp3\n\u002Fnblm slides-download .\u002Fpresentation.pdf\n\u002Fnblm infographic-download .\u002Fvisual.png\n\u002Fnblm media-list                     # List all generated media\n\u002Fnblm media-list --type audio        # List only audio\n\u002Fnblm media-delete \u003Cid>              # Delete a media item\n```\n\n---\n\n# Extended Documentation\n\n## When to Use This Skill\n\nTrigger when user:\n- Mentions NotebookLM explicitly\n- Shares NotebookLM URL (`https:\u002F\u002Fnotebooklm.google.com\u002Fnotebook\u002F...`)\n- Asks to query their notebooks\u002Fdocumentation\n- Wants to add documentation to NotebookLM library\n- Uses phrases like \"ask my NotebookLM\", \"check my docs\", \"query my notebook\"\n\n## ⚠️ CRITICAL: Add Command - Smart Discovery\n\nThe add command now **automatically discovers metadata** from the notebook:\n\n```bash\n# Smart Add (auto-discovers name, description, topics)\npython scripts\u002Frun.py notebook_manager.py add \u003Cnotebook-id-or-url>\n\n# With optional overrides\npython scripts\u002Frun.py notebook_manager.py add \u003Cid> --name \"Custom Name\" --topics \"custom,topics\"\n```\n\n**What Smart Add does:**\n1. Fetches notebook title from NotebookLM API\n2. Queries the notebook content to generate description and topics\n3. Adds to local library with discovered metadata\n\n**Supported input formats:**\n- Notebook ID: `5fd9f36b-8000-401d-a7a0-7aa3f7832644`\n- Full URL: `https:\u002F\u002Fnotebooklm.google.com\u002Fnotebook\u002F5fd9f36b-8000-401d-a7a0-7aa3f7832644`\n\nNEVER manually specify `--name`, `--description`, or `--topics` unless the user explicitly provides them.\n\n## Critical: Always Use run.py Wrapper\n\n**NEVER call scripts directly. ALWAYS use `python scripts\u002Frun.py [script]`:**\n\n```bash\n# ✅ CORRECT - Always use run.py:\npython scripts\u002Frun.py auth_manager.py status\npython scripts\u002Frun.py notebook_manager.py list\npython scripts\u002Frun.py ask_question.py --question \"...\"\n\n# ❌ WRONG - Never call directly:\npython scripts\u002Fauth_manager.py status  # Fails without venv!\n```\n\nThe `run.py` wrapper automatically:\n1. Creates `.venv` if needed\n2. Installs all dependencies\n3. Activates environment\n4. Executes script properly\n\n## Core Workflow\n\n### Step 1: Check Authentication Status\n```bash\npython scripts\u002Frun.py auth_manager.py status\n```\n\nIf not authenticated, proceed to setup.\n\n### Step 2: Authenticate (One-Time Setup)\n```bash\n# Browser MUST be visible for manual Google login\npython scripts\u002Frun.py auth_manager.py setup\n```\n\n**Important:**\n- Browser is VISIBLE for authentication\n- Browser window opens automatically\n- User must manually log in to Google\n- Tell user: \"A browser window will open for Google login\"\n\n### Step 3: Manage Notebook Library\n\n```bash\n# List all notebooks\npython scripts\u002Frun.py notebook_manager.py list\n\n# BEFORE ADDING: Ask user for metadata if unknown!\n# \"What does this notebook contain?\"\n# \"What topics should I tag it with?\"\n\n# Add notebook to library (ALL parameters are REQUIRED!)\npython scripts\u002Frun.py notebook_manager.py add \\\n  --url \"https:\u002F\u002Fnotebooklm.google.com\u002Fnotebook\u002F...\" \\\n  --name \"Descriptive Name\" \\\n  --description \"What this notebook contains\" \\  # REQUIRED - ASK USER IF UNKNOWN!\n  --topics \"topic1,topic2,topic3\"  # REQUIRED - ASK USER IF UNKNOWN!\n\n# Search notebooks by topic\npython scripts\u002Frun.py notebook_manager.py search --query \"keyword\"\n\n# Set active notebook\npython scripts\u002Frun.py notebook_manager.py activate --id notebook-id\n\n# Remove notebook\npython scripts\u002Frun.py notebook_manager.py remove --id notebook-id\n```\n\n### Quick Workflow\n1. Check library: `python scripts\u002Frun.py notebook_manager.py list`\n2. Ask question: `python scripts\u002Frun.py ask_question.py --question \"...\" --notebook-id ID`\n\n### Step 4: Ask Questions\n\n```bash\n# Basic query (uses active notebook if set)\npython scripts\u002Frun.py ask_question.py --question \"Your question here\"\n\n# Query specific notebook\npython scripts\u002Frun.py ask_question.py --question \"...\" --notebook-id notebook-id\n\n# Query with notebook URL directly\npython scripts\u002Frun.py ask_question.py --question \"...\" --notebook-url \"https:\u002F\u002F...\"\n\n# Show browser for debugging\npython scripts\u002Frun.py ask_question.py --question \"...\" --show-browser\n```\n\n## Follow-Up Mechanism (CRITICAL)\n\nEvery NotebookLM answer ends with: **\"EXTREMELY IMPORTANT: Is that ALL you need to know?\"**\n\n**Required Claude Behavior:**\n1. **STOP** - Do not immediately respond to user\n2. **ANALYZE** - Compare answer to user's original request\n3. **IDENTIFY GAPS** - Determine if more information needed\n4. **ASK FOLLOW-UP** - If gaps exist, immediately ask:\n   ```bash\n   python scripts\u002Frun.py ask_question.py --question \"Follow-up with context...\"\n   ```\n5. **REPEAT** - Continue until information is complete\n6. **SYNTHESIZE** - Combine all answers before responding to user\n\n## Z-Library Integration\n\n### Triggers\n- User provides Z-Library URL (zlib.li, z-lib.org, zh.zlib.li)\n- User says \"download this book to NotebookLM\"\n- User says \"add this book from Z-Library\"\n\n### Setup (One-Time)\n```bash\n# Authenticate with Z-Library\npython scripts\u002Frun.py auth_manager.py setup --service zlibrary\n```\n\n### Commands\n```bash\n# Add book from Z-Library\npython scripts\u002Frun.py source_manager.py add --url \"https:\u002F\u002Fzh.zlib.li\u002Fbook\u002F...\"\n\n# Check Z-Library auth status\npython scripts\u002Frun.py auth_manager.py status --service zlibrary\n```\n\n## Script Reference\n\n### Authentication Management (`auth_manager.py`)\n```bash\npython scripts\u002Frun.py auth_manager.py setup                    # Default: Google\npython scripts\u002Frun.py auth_manager.py setup --service google\npython scripts\u002Frun.py auth_manager.py setup --service zlibrary\npython scripts\u002Frun.py auth_manager.py status                   # Show all services\npython scripts\u002Frun.py auth_manager.py status --service zlibrary\npython scripts\u002Frun.py auth_manager.py clear --service zlibrary # Clear auth\n\n# Multi-Account Management (Google)\npython scripts\u002Frun.py auth_manager.py accounts list             # List all accounts\npython scripts\u002Frun.py auth_manager.py accounts add              # Add new account\npython scripts\u002Frun.py auth_manager.py accounts switch 1         # Switch by index\npython scripts\u002Frun.py auth_manager.py accounts switch user@gmail.com  # Switch by email\npython scripts\u002Frun.py auth_manager.py accounts remove 2         # Remove account\n```\n\n### Notebook Management (`notebook_manager.py`)\n```bash\npython scripts\u002Frun.py notebook_manager.py add --url URL --name NAME --description DESC --topics TOPICS\n# OR use notebook ID directly:\npython scripts\u002Frun.py notebook_manager.py add --notebook-id ID --name NAME --description DESC --topics TOPICS\npython scripts\u002Frun.py notebook_manager.py list\npython scripts\u002Frun.py notebook_manager.py search --query QUERY\npython scripts\u002Frun.py notebook_manager.py activate --id ID\npython scripts\u002Frun.py notebook_manager.py remove --id ID\npython scripts\u002Frun.py notebook_manager.py stats\n```\n\n### Question Interface (`ask_question.py`)\n```bash\npython scripts\u002Frun.py ask_question.py --question \"...\" [--notebook-id ID] [--notebook-url URL] [--show-browser]\n```\n\n### Source Manager (`source_manager.py`)\n```bash\n# Upload to active notebook\npython scripts\u002Frun.py source_manager.py add --file \"\u002Fpath\u002Fto\u002Fbook.pdf\" --use-active\n\n# Create new notebook for upload\npython scripts\u002Frun.py source_manager.py add --file \"\u002Fpath\u002Fto\u002Fbook.pdf\" --create-new\n\n# Upload to specific notebook\npython scripts\u002Frun.py source_manager.py add --file \"\u002Fpath\u002Fto\u002Fbook.pdf\" --notebook-id NOTEBOOK_ID\n\n# Z-Library download and upload\npython scripts\u002Frun.py source_manager.py add --url \"https:\u002F\u002Fzh.zlib.li\u002Fbook\u002F...\" --use-active\npython scripts\u002Frun.py source_manager.py add --url \"https:\u002F\u002Fzh.zlib.li\u002Fbook\u002F...\" --create-new\n\n# Sync a folder (new!)\npython scripts\u002Frun.py source_manager.py sync \"\u002Fpath\u002Fto\u002Fdocs\" --use-active\npython scripts\u002Frun.py source_manager.py sync \"\u002Fpath\u002Fto\u002Fdocs\" --create-new\npython scripts\u002Frun.py source_manager.py sync \"\u002Fpath\u002Fto\u002Fdocs\" --notebook-id NOTEBOOK_ID\n\n# Sync options (new!)\npython scripts\u002Frun.py source_manager.py sync \"\u002Fpath\u002Fto\u002Fdocs\" --dry-run    # Preview only\npython scripts\u002Frun.py source_manager.py sync \"\u002Fpath\u002Fto\u002Fdocs\" --rebuild   # Force re-hash all files\n```\n\n**Folder Sync:**\n- Scans folder for supported types: PDF, TXT, MD, DOCX, HTML, EPUB\n- Tracks sync state internally (no per-folder tracking file to manage)\n- Sync strategy: add new, update modified (delete + re-upload), skip unchanged\n- Multi-account aware (tracks which Google account was used)\n**Note:** One of `--use-active`, `--create-new`, or `--notebook-id` is REQUIRED.\nUploads wait for NotebookLM processing and print progress as `Ready: N\u002FT`. Press Ctrl+C to stop waiting.\nLocal file uploads use browser automation and require Google authentication.\nIf browser automation is unavailable, set `NOTEBOOKLM_UPLOAD_MODE=text` to upload extracted text instead (PDFs require `pypdf`).\n\n### Data Cleanup (`cleanup_manager.py`)\n```bash\npython scripts\u002Frun.py cleanup_manager.py                    # Preview cleanup\npython scripts\u002Frun.py cleanup_manager.py --confirm          # Execute cleanup\npython scripts\u002Frun.py cleanup_manager.py --preserve-library # Keep notebooks\n```\n\n### Watchdog Status (`auth_manager.py`)\n```bash\npython scripts\u002Frun.py auth_manager.py watchdog-status\n```\n\n## Environment Management\n\nThe virtual environment is automatically managed:\n- First run creates `.venv` automatically\n- Dependencies install automatically\n- Node.js dependencies install automatically\n- agent-browser daemon starts on demand and keeps browser state in memory\n- daemon stops after 10 minutes of inactivity (any agent-browser command resets the timer)\n- set `AGENT_BROWSER_OWNER_PID` to auto-stop when the agent process exits\n- `scripts\u002Frun.py` sets `AGENT_BROWSER_OWNER_PID` to its parent PID by default\n- Everything isolated in skill directory\n\nManual setup (only if automatic fails):\n```bash\npython -m venv .venv\nsource .venv\u002Fbin\u002Factivate  # Linux\u002FMac\npip install -r requirements.txt\nnpm install\nnpm run install-browsers\n```\n\n## Data Storage\n\nAll data stored in `~\u002F.claude\u002Fskills\u002Fnotebooklm\u002Fdata\u002F`:\n- `library.json` - Notebook metadata (with account associations)\n- `auth\u002Fgoogle\u002F` - Multi-account Google auth\n  - `index.json` - Account index (active account, list)\n  - `\u003Cn>-\u003Cemail>.json` - Per-account credentials\n- `auth\u002Fzlibrary.json` - Z-Library auth state\n- `agent_browser\u002Fsession_id` - Current daemon session ID\n- `agent_browser\u002Flast_activity.json` - Last activity timestamp for idle shutdown\n- `agent_browser\u002Fwatchdog.pid` - Idle watchdog process ID\n\n**Security:** Protected by `.gitignore`, never commit to git.\n\n## Configuration\n\nOptional `.env` file in skill directory:\n```env\nHEADLESS=false           # Browser visibility\nSHOW_BROWSER=false       # Default browser display\nSTEALTH_ENABLED=true     # Human-like behavior\nTYPING_WPM_MIN=160       # Typing speed\nTYPING_WPM_MAX=240\nDEFAULT_NOTEBOOK_ID=     # Default notebook\n```\n\n## Decision Flow\n\n```\nUser mentions NotebookLM\n    ↓\nCheck auth → python scripts\u002Frun.py auth_manager.py status\n    ↓\nIf not authenticated → python scripts\u002Frun.py auth_manager.py setup\n    ↓\nCheck\u002FAdd notebook → python scripts\u002Frun.py notebook_manager.py list\u002Fadd (with --description)\n    ↓\nActivate notebook → python scripts\u002Frun.py notebook_manager.py activate --id ID\n    ↓\nAsk question → python scripts\u002Frun.py ask_question.py --question \"...\"\n    ↓\nSee \"Is that ALL you need?\" → Ask follow-ups until complete\n    ↓\nSynthesize and respond to user\n```\n\n## Troubleshooting\n\n| Problem | Solution |\n|---------|----------|\n| ModuleNotFoundError | Use `run.py` wrapper |\n| Authentication fails | Browser must be visible for setup! --show-browser |\n| DAEMON_UNAVAILABLE | Ensure Node.js\u002Fnpm installed, run `npm install`, retry |\n| AUTH_REQUIRED | Run `python scripts\u002Frun.py auth_manager.py setup` |\n| ELEMENT_NOT_FOUND | Verify notebook URL and re-run with fresh page load |\n| Rate limit (50\u002Fday) | Wait or add another Google account with `accounts add` |\n| Browser crashes | `python scripts\u002Frun.py cleanup_manager.py --preserve-library` |\n| Notebook not found | Check with `notebook_manager.py list` |\n\n## Best Practices\n\n1. **Always use run.py** - Handles environment automatically\n2. **Check auth first** - Before any operations\n3. **Follow-up questions** - Don't stop at first answer\n4. **Browser visible for auth** - Required for manual login\n5. **Include context** - Each question is independent\n6. **Synthesize answers** - Combine multiple responses\n\n## Limitations\n\n- No session persistence (each question = new browser)\n- Rate limits on free Google accounts (50 queries\u002Fday per account; use multiple accounts to increase)\n- Manual upload required (user must add docs to NotebookLM)\n- Browser overhead (few seconds per question)\n\n## Resources (Skill Structure)\n\n**Important directories and files:**\n\n- `scripts\u002F` - All automation scripts (ask_question.py, notebook_manager.py, etc.)\n- `data\u002F` - Local storage for authentication and notebook library\n- `references\u002F` - Extended documentation:\n  - `api_reference.md` - Detailed API documentation for all scripts\n  - `troubleshooting.md` - Common issues and solutions\n  - `usage_patterns.md` - Best practices and workflow examples\n- `.venv\u002F` - Isolated Python environment (auto-created on first run)\n- `.gitignore` - Protects sensitive data from being committed\n",{"name":5,"description":7},"main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fmagicseek\u002Fnblm",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill nblm",{"tool":39,"command":40},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill nblm",{"tool":42,"command":43},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill nblm","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmagicseek\u002Fnblm\u002FSKILL.md",true,[],[48,56,63,70,77,84],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":55},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":55},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":55},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":55},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":55},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":55},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]