{"id":"claude-world-notebooklm-skill","name":"notebooklm-skill","homepage":"https://youtu.be/6M3K4sxahdE","repo_url":"https://github.com/claude-world/notebooklm-skill","category":"ai-ml","subcategories":[],"tags":["ai-ml","devtools","automation","mcp-server","claude-code","research","content-generation","python"],"what_it_does":"notebooklm-skill bridges NotebookLM research with Claude-style content generation and distribution. It ingests URLs/PDFs/trending topics, creates and manages NotebookLM notebooks, runs deep research/QA with citations, generates multiple artifact types (text and downloadable assets like audio/video/slides/reports and some structured outputs), and can run as a CLI tool, a Claude Code Skill, or an MCP server for agent-driven workflows.","use_cases":["Research-to-article pipelines from URLs, PDFs, and arXiv sources","Deep research Q&A with citations for drafting content","Trending-topic discovery followed by automated notebook research and content generation","Generating social posts/threads/newsletters from research outputs","Batch generation of learning artifacts (slides, podcasts, quizzes, flashcards, study guides, etc.)","Agent workflows via MCP tools (create/list/add-source/ask/summarize/generate/download/research/trend-research)"],"not_for":["Purely offline or air-gapped usage (implied by web/PDF ingestion and upstream services)","Requirements for an official REST/GraphQL/SDK-based developer API (primarily CLI + MCP)","Use cases needing documented rate-limit headers/guarantees or a published SLA for uptime","Highly regulated environments that require explicit compliance and data-residency guarantees"],"best_when":"You want an agent-friendly research-and-content pipeline that can be driven programmatically (MCP) or from the command line, with Google-browser login already acceptable.","avoid_when":"You need fine-grained authorization controls (scopes), strict error-code contracts, or strong operational guarantees like documented SLAs and robust retry/idempotency semantics.","alternatives":["A pure notebooklm-py workflow (manual orchestration without the Claude Code/MCP skill layer)","Other MCP/agent wrappers around NotebookLM (if available) or custom wrappers using notebooklm-py","Custom pipelines using feedparser + scraping + LLM summarization without NotebookLM’s research notebook abstraction"],"af_score":55.0,"security_score":56.0,"reliability_score":30.0,"package_type":"skill","discovery_source":["openclaw"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T13:42:44.073894+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["Browser-based Google login (via notebooklm-py session storage)","One-time CLI login that stores session state in ~/.notebooklm/storage_state.json"],"oauth":false,"scopes":false,"notes":"Authentication is described as browser-based Google login with stored session cookies/state for subsequent CLI/MCP calls. No API-key/OAuth client/explicit scopes are documented in the provided README."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"The provided material does not describe pricing tiers for notebooklm-skill itself; it appears to rely on upstream NotebookLM usage and Google login for access, but costs are not documented here."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":55.0,"security_score":56.0,"reliability_score":30.0,"mcp_server_quality":55.0,"documentation_accuracy":70.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":70.0,"rate_limit_clarity":10.0,"tls_enforcement":90.0,"auth_strength":55.0,"scope_granularity":10.0,"dependency_hygiene":55.0,"secret_handling":70.0,"security_notes":"The README emphasizes session storage for Google browser login (no API keys). However, it does not document transport security guarantees, fine-grained scopes/authorization boundaries, audit logging, or how secrets/tokens are handled within the MCP/CLI processes. Dependency security posture is not verifiable from the provided content; presence of Playwright/httpx suggests additional surface area.","uptime_documented":0.0,"version_stability":45.0,"breaking_changes_history":40.0,"error_recovery":35.0,"idempotency_support":"false","idempotency_notes":"No explicit idempotency guarantees documented for notebook creation, deletions, or artifact generation; repeated calls may create duplicate notebooks/artifacts depending on server behavior.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Session-based Google login is required; expired sessions may cause auth errors until re-login","Infographic is listed as excluded from downloadable types (possible mismatch with agent expectations around downloadable artifacts)","Audio format is M4A (not MP3), which can break downstream media tooling if assumed otherwise","No explicit rate-limit or retry/backoff strategy is described in the provided README"]}}