{"id":47236894,"url":"https://github.com/claude-world/notebooklm-skill","last_synced_at":"2026-04-01T17:21:07.331Z","repository":{"id":344261302,"uuid":"1181147940","full_name":"claude-world/notebooklm-skill","owner":"claude-world","description":"NotebookLM does the research, Claude writes the content. Research → Synthesis → Content Creation → Publishing. Claude Code Skill + MCP Server.","archived":false,"fork":false,"pushed_at":"2026-03-24T14:24:03.000Z","size":269,"stargazers_count":141,"open_issues_count":5,"forks_count":14,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-27T13:34:06.940Z","etag":null,"topics":["ai-research","claude-code","claude-code-skill","content-pipeline","mcp-server","notebooklm","notebooklm-py","podcast-generator"],"latest_commit_sha":null,"homepage":"https://youtu.be/6M3K4sxahdE","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/claude-world.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-03-13T19:57:38.000Z","updated_at":"2026-03-27T10:09:48.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/claude-world/notebooklm-skill","commit_stats":null,"previous_names":["claude-world/notebooklm-skill"],"tags_count":5,"template":false,"template_full_name":null,"purl":"pkg:github/claude-world/notebooklm-skill","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/claude-world%2Fnotebooklm-skill","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/claude-world%2Fnotebooklm-skill/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/claude-world%2Fnotebooklm-skill/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/claude-world%2Fnotebooklm-skill/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/claude-world","download_url":"https://codeload.github.com/claude-world/notebooklm-skill/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/claude-world%2Fnotebooklm-skill/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31290537,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-01T13:12:26.723Z","status":"ssl_error","status_checked_at":"2026-04-01T13:12:25.102Z","response_time":53,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-research","claude-code","claude-code-skill","content-pipeline","mcp-server","notebooklm","notebooklm-py","podcast-generator"],"created_at":"2026-03-13T23:08:04.963Z","updated_at":"2026-04-01T17:21:07.305Z","avatar_url":"https://github.com/claude-world.png","language":"Python","readme":"# notebooklm-skill\n\n\u003e NotebookLM does the research, Claude writes the content.\n\nThe only tool that connects trending topic discovery → NotebookLM deep research → AI content creation → multi-platform publishing. Works as a Claude Code Skill or standalone MCP Server.\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n\n**[繁體中文版 README](README.zh-TW.md)**\n\n---\n\n## Demo\n\n| Language | YouTube | Slides |\n|----------|---------|--------|\n| English | [Watch](https://youtu.be/q1kj_OccaVE) | 6 pages, auto-generated |\n| 繁體中文 | [Watch](https://youtu.be/6M3K4sxahdE) | 5 pages, auto-generated |\n\nAll slides, podcasts, and videos were generated by NotebookLM using this tool.\n\n---\n\n## What is this?\n\n**notebooklm-skill** bridges NotebookLM's research capabilities with Claude's content generation. Feed it URLs, PDFs, or trending topics — it creates a NotebookLM notebook, runs deep research queries, and hands structured findings to Claude for polished output: articles, social posts, newsletters, podcasts, or any format you need.\n\nBuilt on [notebooklm-py](https://pypi.org/project/notebooklm-py/) v0.3.4 — pure async Python, no OAuth setup needed.\n\n```\nSources (URLs, PDFs)          NotebookLM                Claude               Artifacts \u0026 Platforms\n+-----------------+    +------------------+    +-----------------+    +----------------------+\n| Web articles    |---\u003e| Create notebook  |---\u003e| Draft article   |---\u003e| Blog / CMS           |\n| Research papers |    | Add sources      |    | Social posts    |    | Threads / X          |\n| YouTube videos  |    | Ask questions    |    | Newsletter      |    | Newsletter           |\n| Trending topics |    | Extract insights |    | Any format      |    | Any platform         |\n+-----------------+    +------------------+    +-----------------+    +----------------------+\n     Phase 1                Phase 2                Phase 3                  Phase 4\n                                |\n                                v\n                       +------------------+\n                       | Generate artifacts|\n                       | Audio (podcast)   |\n                       | Video             |\n                       | Slides            |\n                       | Report            |\n                       | Quiz              |\n                       | Flashcards        |\n                       | Mind map          |\n                       | Infographic       |\n                       | Data table        |\n                       | Study guide       |\n                       +------------------+\n                            Phase 2b\n```\n\n## Quick Start\n\n```bash\n# Option A: uvx (recommended — zero install)\nuvx notebooklm-skill --help\nuvx --from notebooklm-skill notebooklm-mcp   # Start MCP server\n\n# Option B: pip install from PyPI\npip install notebooklm-skill\n\n# Option C: Install from source\ngit clone https://github.com/claude-world/notebooklm-skill.git\ncd notebooklm-skill \u0026\u0026 pip install .\n\n# Option D: One-line install (pip + Playwright + Claude Code Skill)\ngit clone https://github.com/claude-world/notebooklm-skill.git\ncd notebooklm-skill \u0026\u0026 ./install.sh\n\n# Authenticate with Google (one-time, opens browser)\nuvx notebooklm login              # if using uvx\n# or: python3 -m notebooklm login  # if using pip install\n\n# Use commands (uvx or direct — both work the same)\nnotebooklm-skill create --title \"My Research\" --sources https://example.com/article\nnotebooklm-skill ask --notebook \"My Research\" --query \"What are the key findings?\"\nnotebooklm-skill podcast --notebook \"My Research\" --lang en --output podcast.m4a\nnotebooklm-pipeline research-to-article --sources https://example.com --title \"Topic\"\nnotebooklm-mcp                   # Start MCP server (stdio mode)\n```\n\nOr use scripts directly: `python scripts/notebooklm_client.py create ...`\n\nSee [docs/SETUP.md](docs/SETUP.md) for the full setup guide.\n\n## Authentication\n\nnotebooklm-py uses browser-based Google login. No API keys, no OAuth Client ID, no Google Cloud project needed.\n\n```bash\n# One-time login (opens Chromium, sign in with Google)\nuvx notebooklm login              # if using uvx\npython3 -m notebooklm login       # if using pip install\n```\n\n| Step | Command | What happens |\n|------|---------|-------------|\n| **Login** | `uvx notebooklm login` | Opens Chromium, user logs into Google |\n| **Session storage** | Automatic | Saved to `~/.notebooklm/storage_state.json` |\n| **Subsequent use** | All CLI / MCP commands | Reads saved session, pure HTTP calls |\n| **Verify** | `uvx notebooklm-skill list` | Lists notebooks to confirm auth works |\n| **Clear** | `rm -rf ~/.notebooklm` | Removes stored session |\n\nSession typically lasts weeks. Re-run `login` if you get authentication errors.\n\n## Two Ways to Use\n\n| | **Claude Code Skill** | **MCP Server** |\n|---|---|---|\n| **Best for** | Claude Code users who want NotebookLM in their workflow | Any MCP-compatible client (Cursor, Gemini CLI, etc.) |\n| **Setup** | Copy skill to `.claude/skills/` | Add server to MCP config |\n| **Invocation** | Claude auto-detects when relevant | Tools appear in client tool list |\n| **Config** | `SKILL.md` + `.env` | `.mcp.json` + `.env` |\n| **Requirements** | Python 3.10+, notebooklm-py | Python 3.10+, notebooklm-py |\n\n## Features\n\n| Feature | Description | Status |\n|---|---|---|\n| **Notebook CRUD** | Create, list, delete notebooks | Available |\n| **Source ingestion** | Add URLs, PDFs, YouTube links, plain text | Available |\n| **Research queries** | Ask questions against notebook sources with citations | Available |\n| **Structured extraction** | Get key facts, arguments, timelines | Available |\n| **Content generation** | Use research output as context for Claude | Available |\n| **Batch operations** | Process multiple sources or queries at once | Available |\n| **trend-pulse integration** | Auto-discover trending topics to research | Available |\n| **threads-viral-agent integration** | Publish research-backed social posts | Available |\n\n### Artifact Generation (9 downloadable types)\n\n| Artifact | Format | Description |\n|---|---|---|\n| **Audio** | M4A | AI-generated podcast discussion |\n| **Video** | MP4 | Video summary with visuals |\n| **Slides** | PDF / PPTX | Presentation deck |\n| **Report** | Markdown | Comprehensive written report |\n| **Quiz** | JSON / Markdown / HTML | Multiple-choice assessment questions |\n| **Flashcards** | JSON / Markdown / HTML | Study flashcard deck |\n| **Mind map** | JSON | Visual concept map |\n| **Infographic** | PNG | Visual data summary |\n| **Data table** | CSV | Structured data extraction |\n| **Study guide** | Markdown | Structured learning material |\n\nMost artifacts support language selection (e.g., `--lang zh-TW`). Exceptions: quiz, flashcards, mind-map.\n\n\u003e **Note**: NotebookLM returns audio in MPEG-4 (M4A) format, not MP3.\n\n## Architecture\n\n```\n+---------------------------------------------------------------+\n|                      notebooklm-skill                          |\n|                                                                |\n|  +---------+  +--------------+  +----------+  +------------+  |\n|  | Phase 1 |  |   Phase 2    |  |  Phase 3 |  |  Phase 4   |  |\n|  | Collect  |-\u003e|  Research    |-\u003e| Generate  |-\u003e|  Publish   |  |\n|  +---------+  +--------------+  +----------+  +------------+  |\n|      |              |                |               |         |\n|  +--------+  +-------------+  +-----------+  +-----------+    |\n|  | URLs   |  | NotebookLM  |  |  Claude    |  | Threads   |    |\n|  | PDFs   |  | (via        |  |  Content   |  | Blog      |    |\n|  | RSS    |  |  notebooklm |  |  Engine    |  | Email     |    |\n|  | Trends |  |  -py 0.3.4) |  |            |  | CMS       |    |\n|  +--------+  | - notebooks |  +-----------+  +-----------+    |\n|              | - sources   |        |                          |\n|              | - chat/ask  |  +-----------+                    |\n|              | - artifacts |  | Artifacts |                    |\n|              +-------------+  | audio     |                    |\n|                               | video     |                    |\n|                               | slides    |                    |\n|                               | report    |                    |\n|                               | quiz      |                    |\n|                               | flashcards|                    |\n|                               | mind-map  |                    |\n|                               | infographic| ⚠️ no download    |\n|                               | data-table|                    |\n|                               | study-guide|                   |\n|                               +-----------+                    |\n|                                                                |\n|  +-----------------------------------------------------------+ |\n|  |  Interfaces                                                | |\n|  |  +-- scripts/          CLI tools (notebooklm-py direct)   | |\n|  |  +-- mcp_server/       MCP protocol server                 | |\n|  |  +-- SKILL.md          Claude Code skill definition        | |\n|  +-----------------------------------------------------------+ |\n+---------------------------------------------------------------+\n         ^                                          ^\n         |                                          |\n   +-----------+                             +-----------+\n   |trend-pulse|                             |threads-   |\n   |(optional) |                             |viral-agent|\n   +-----------+                             |(optional) |\n                                             +-----------+\n```\n\n## Usage Examples\n\n### 1. Research to Article\n\n```bash\npython scripts/pipeline.py research-to-article \\\n  --sources \"https://arxiv.org/abs/2401.00001\" \\\n            \"https://blog.example.com/ai-agents\" \\\n  --title \"AI Agent Survey\"\n```\n\n### 2. Research to Social Posts\n\n```bash\npython scripts/pipeline.py research-to-social \\\n  --sources \"https://example.com/ai-news\" \\\n  --platform threads \\\n  --title \"AI News This Week\"\n```\n\n### 3. Trending Topics to Content\n\n```bash\npython scripts/pipeline.py trend-to-content \\\n  --geo TW \\\n  --count 5 \\\n  --platform threads\n```\n\n### 4. RSS Batch Digest\n\n```bash\npython scripts/pipeline.py batch-digest \\\n  --rss \"https://example.com/feed.xml\" \\\n  --title \"Weekly AI Digest\"\n```\n\n### 5. Generate All Artifacts\n\n```bash\npython scripts/pipeline.py generate-all \\\n  --sources \"https://example.com/article\" \\\n  --title \"Research\" \\\n  --output-dir ./output \\\n  --language zh-TW\n```\n\n### 6. Slides + Podcast → YouTube Video\n\nCombine NotebookLM-generated slides and podcast into a YouTube-ready video:\n\n```bash\n# Generate slides and podcast\npython scripts/notebooklm_client.py generate --notebook \"Research\" --type slides\npython scripts/notebooklm_client.py podcast --notebook \"Research\" --lang en --output podcast.m4a\npython scripts/notebooklm_client.py download --notebook \"Research\" --type slides --output slides.pdf\n\n# Convert PDF to PNG + compose video\n./scripts/make_video.sh slides.pdf podcast.m4a output.mp4\n```\n\n## Pipeline Workflows\n\n| Workflow | Input | Output | Steps |\n|---|---|---|---|\n| `research-to-article` | URLs, text | Article draft JSON | Create notebook → 5 research questions → article draft |\n| `research-to-social` | URLs, text | Social post draft | Create notebook → summarize → platform-specific post |\n| `trend-to-content` | Geo, count | Content per trend | Fetch trends → create notebooks → research → draft |\n| `batch-digest` | RSS URL | Newsletter digest | Fetch RSS → create notebook → digest + Q\u0026A |\n| `generate-all` | URLs, text | Audio, video, PDF, etc. | Create notebook → generate all artifacts → download |\n\n## MCP Server Setup\n\nAdd to your project's `.mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"notebooklm\": {\n      \"command\": \"uvx\",\n      \"args\": [\"--from\", \"notebooklm-skill\", \"notebooklm-mcp\"]\n    }\n  }\n}\n```\n\nOr if you installed via `pip install notebooklm-skill`:\n\n```json\n{\n  \"mcpServers\": {\n    \"notebooklm\": {\n      \"command\": \"notebooklm-mcp\"\n    }\n  }\n}\n```\n\nWorks with Claude Code, Cursor, Gemini CLI, and any MCP-compatible client.\n\n## Claude Code Skill Setup\n\n```bash\n# Option A: Symlink (auto-updates with git pull)\n./install.sh\n\n# Option B: Manual copy\nmkdir -p .claude/skills/notebooklm\ncp /path/to/notebooklm-skill/SKILL.md .claude/skills/notebooklm/\ncp /path/to/notebooklm-skill/scripts/*.py .claude/skills/notebooklm/scripts/\ncp /path/to/notebooklm-skill/requirements.txt .claude/skills/notebooklm/\n\n# Authenticate (one-time)\npython3 -m notebooklm login\n```\n\nClaude will automatically detect the skill when you ask about research, NotebookLM, or content creation.\n\n## API Reference\n\n### CLI Commands (11)\n\n| Command | Description |\n|---|---|\n| `create` | Create a notebook with URL/text sources |\n| `list` | List all notebooks |\n| `delete` | Delete a notebook |\n| `add-source` | Add a source (URL, text, or file) to existing notebook |\n| `ask` | Ask a research question (returns answer + citations) |\n| `summarize` | Get notebook summary |\n| `generate` | Generate an artifact (audio, video, slides, etc.) |\n| `download` | Download a generated artifact |\n| `research` | Run deep web research |\n| `podcast` | Shortcut for `generate --type audio` (auto-downloads) |\n| `qa` | Shortcut for `generate --type quiz` |\n\n### MCP Tools (13)\n\n| Tool | Description |\n|---|---|\n| `nlm_create_notebook` | Create notebook with sources |\n| `nlm_list` | List all notebooks |\n| `nlm_delete` | Delete a notebook |\n| `nlm_add_source` | Add source to existing notebook |\n| `nlm_ask` | Ask question (returns answer + citations) |\n| `nlm_summarize` | Get notebook summary |\n| `nlm_generate` | Generate artifact (9 types, infographic excluded) |\n| `nlm_download` | Download generated artifact |\n| `nlm_list_sources` | List sources in notebook |\n| `nlm_list_artifacts` | List generated artifacts |\n| `nlm_research` | Deep web research |\n| `nlm_research_pipeline` | Full research pipeline |\n| `nlm_trend_research` | Trend → research pipeline |\n\n## Integrations\n\n- **[trend-pulse](https://github.com/claude-world/trend-pulse)** — Real-time trending topic discovery from 7 sources\n- **[threads-viral-agent](https://github.com/claude-world/claude-world.com)** — Auto-publish research-backed social posts\n\n## Contributing\n\n1. Fork the repository\n2. Create a feature branch (`git checkout -b feature/amazing-feature`)\n3. Commit your changes\n4. Push and open a Pull Request\n\n```bash\n# Development setup\ngit clone https://github.com/claude-world/notebooklm-skill.git\ncd notebooklm-skill\npip install -e .\npython3 -m notebooklm login\npython -m pytest tests/\n```\n\n## License\n\nMIT License. See [LICENSE](LICENSE).\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fclaude-world%2Fnotebooklm-skill","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fclaude-world%2Fnotebooklm-skill","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fclaude-world%2Fnotebooklm-skill/lists"}