Nlm Skill
If you're automating Google NotebookLM workflows, this gets you there via CLI or MCP server. It covers the full spectrum: spinning up notebooks, pulling in sources from URLs, YouTube, or Google Drive, generating podcasts and reports, and running research queries. The authentication flow is straightforward but sessions only last about 20 minutes, so you'll be re-logging periodically. One thing to watch: it includes both CLI commands and MCP tools, and if you have both available, you need to pick one approach upfront. The skill is careful about destructive operations and warns you before deletions, which is good hygiene. Useful if you're building content pipelines or need programmatic access to NotebookLM's generation features.
- skills.sh installs
- 184
- GitHub stars
- 4.7K
- last updated
- Jun 3, 2026
Install
$ npx -y skills add jacob-bd/notebooklm-mcp-cli --skill nlm-skill --agent claude-codeInstalls into .claude/skills of the current project.
Files
Gemini Notebook CLI & MCP Expert
This skill provides comprehensive guidance for using Gemini Notebook via both the nlm CLI and MCP tools.
Tool Detection (CRITICAL - Read First!)
ALWAYS check which tools are available before proceeding:
- Check for MCP tools: Tool names vary by host; look for
mcp__gemini-notebook-mcp__*,mcp__notebooklm_mcp__*, ormcp_gemini_notebook_mcp_*. - Follow an explicit surface choice: If the user asks for MCP or CLI, use it.
- Choose by task when both are available: Use MCP for notebook operations and downloads inside its configured download directory. Use the CLI for an explicit
--profilewithout changing the MCP default account, or for a user-directed output path outside the MCP download directory. Ask only if the choice would materially change the result and the user's preference is unclear. - Use the available surface when only MCP or only CLI is callable; read its tool docstring or
nlm <command> --helpbefore supplying unfamiliar options.
Decision Logic:
has_mcp_tools = check_available_tools() # Look for any NotebookLM MCP tool name above
has_cli = check_bash_available() # Can run nlm commands
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/jacob-bd/notebooklm-mcp-cli
- Categories
- AI & Agent Building, CLI & Terminal
- First seen
- Jun 3, 2026
Recommended
More AI & Agent Building
directory-managementawslabs/agent-pluginsManages project directory setup and artifact organization. Use when starting a new project, resuming an existing one, or when a PLAN.md needs to be associated w183skills.sh installs
databricks-python-sdkdatabricks-solutions/ai-dev-kitDatabricks development guidance including Python SDK, Databricks Connect, CLI, and REST API. Use when working with databricks-sdk, databricks-connect, or Databr183skills.sh installs
data-engineerdaffy0208/ai-dev-standardsExpert in data pipelines, ETL processes, and data infrastructure181skills.sh installsforensic-data-engineerdaffy0208/ai-dev-standardsExpert in data forensics, anomaly detection, audit trail analysis, fraud detection, and breach investigation181skills.sh installs
brutal-honesty-reviewproffesor-for-testing/agentic-qeUnvarnished technical criticism combining Linus Torvalds' precision, Gordon Ramsay's standards, and James Bach's BS-detection. Use when code/tests need harsh re181skills.sh installs
security-hardeningancoleman/ai-design-componentsReduces attack surface across OS, container, cloud, network, and database layers using CIS Benchmarks and zero-trust principles. Use when hardening production i180skills.sh installs