agentleFS
afaraha8403afaraha8403/balakit/.agents/skills/nlm-skill/SKILL.md

nlm-skill

Skill1 starsChanged 10 days agoMITView on GitHub

Expert guide for the NotebookLM CLI (nlm) and MCP server. Covers authentication, notebook management, source addition (URLs, YouTube, text, Drive, files), content generation (audio, video, report, quiz, flashcards, mind map, slides, infographic, data table), research, artifact management, and automation workflows. Progressive disclosure: body carries critical rules + decision tree + phase workflow; full command reference in references/. Triggers on "nlm", "notebooklm", "notebook lm", "podcast generation", "audio overview", or any NotebookLM automation task.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 4 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check for MCP tools: Look for tools starting with mcp__notebooklm-mcp__*.

    line 51
  2. Distinctive:

    If BOTH MCP tools AND CLI are available: ASK the user which they prefer.

    line 52
  3. Distinctive:

    If only MCP tools are available: Use them directly (see references/mcp_tools.md).

    line 53
  4. Very specific:

    If only CLI is available: Use nlm CLI commands via Bash (see references/command_reference.md).

    line 55
  5. Very specific:

    Always authenticate first: Run nlm login before any operations.

    line 72
  6. Very specific:

    --confirm is REQUIRED: All generation and delete commands need --confirm / -y (CLI) or confirm=True (MCP).

    line 77
  7. Distinctive:

    Capture IDs from output: Create/start commands return IDs needed for subsequent operations.

    line 81
  8. Very specific:

    DO NOT launch REPL: Never nlm chat start — it opens an interactive REPL that AI tools cannot control.

    line 86
  9. Very specific:

    Output format: Default (no flags) = compact + token-efficient.

    line 89
  10. Distinctive:

    Wait between operations to avoid rate limits:

    line 160

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

NotebookLM CLI & MCP Expert

Leading words: nlm, NotebookLM, audio overview, studio artifacts, progressive disclosure, phase separation, confirm-required, capture IDs, alias shortcuts, no REPL.

This skill provides comprehensive guidance for using NotebookLM via both the nlm CLI and MCP tools. The body carries the critical rules, the tool detection decision tree, and the 3-phase workflow. Depth lives in references/ behind context pointers.

Tool Detection (CRITICAL — read first)

ALWAYS check which tools are available before proceeding:

  1. Check for MCP tools: Look for tools starting with mcp__notebooklm-mcp__*.
  2. If BOTH MCP tools AND CLI are available: ASK the user which they prefer.
  3. If only MCP tools are available: Use them directly (see references/mcp_tools.md).
  4. If only CLI is available: Use nlm CLI commands via Bash (see references/command_reference.md).
has_mcp_tools = check_available_tools()  # mcp__notebooklm-mcp__*
has_cli = check_bash_available()         # Can run nlm commands

if has_mcp_tools and has_cli:
    user_preference = ask_user()
else if has_mcp_tools:
    use_mcp_tools()
else:
    use_cli()

Critical Rules (read first)

  1. Always authenticate first: Run nlm login before any operations.
  2. Sessions expire in ~20 minutes: Re-run nlm login if commands start failing with auth errors.
  3. ⚠️ ALWAYS ASK USER BEFORE DELETE: Deletions are irreversible. Show what will be deleted and warn about permanent data loss.
  4. --confirm is REQUIRED: All generation and delete commands need --confirm / -y (CLI) or confirm=True (MCP).
  5. Research requires --notebook-id: The flag is mandatory, not positional.
  6. Capture IDs from output: Create/start commands return IDs needed for subsequent operations.
  7. Use aliases: nlm alias set <name> <uuid> simplifies long UUIDs.
  8. Check aliases before creating: nlm alias list first to avoid name conflicts.
  9. DO NOT launch REPL: Never nlm chat start — it opens an interactive REPL that AI tools cannot control. Use nlm notebook query for one-shot Q&A.
  10. Output format: Default (no flags) = compact + token-efficient. --quiet captures IDs for piping. --json only when parsing fields.
  11. Use --help when unsure: nlm <command> --help shows options.

Phase 1 — Authenticate

- [ ] nlm login (launches browser, extracts cookies — primary method)
- [ ] nlm login --check (validate current session)
- [ ] If multi-account: nlm login --profile <name>; nlm login switch <name>
- [ ] If MCP only and auth fails: mcp__notebooklm-mcp__refresh_auth()

🛑 Checkpoint: Confirm authentication is valid before any other operation. Re-authenticate if session > 20 minutes old.

Phase 2 — Operate

- [ ] List/find notebook: nlm notebook list, or use an alias.
- [ ] Add sources: --url (web/YouTube), --text, --drive <doc-id>,
      --file "/path" --wait.
- [ ] Research new sources: nlm research start "query" --notebook-id <id>
      (--mode fast|deep, --source web|drive).
- [ ] Poll research: nlm research status <id> --max-wait 300.
- [ ] Import: nlm research import <id> <task-id> [--indices ...] [--cited-only].
- [ ] Manage aliases: nlm alias set|get|list|delete.
- [ ] Query sources: nlm notebook query <id> "question" (--source-ids to scope).

Pull references/command_reference.md for full CLI command signatures and options.

Phase 3 — Generate

- [ ] Pick artifact: audio | video | report | quiz | flashcards | mindmap |
      slides | infographic | data-table.
- [ ] ALWAYS require --confirm (CLI) or confirm=True (MCP).
- [ ] Poll status: nlm studio status <nb-id>.
- [ ] Download: nlm download audio|video|report|slide-deck|quiz <nb-id>
      --output <path>.
- [ ] Export to Docs/Sheets: nlm export docs|sheets <nb-id> <artifact-id>
      --title "...".
- [ ] Delete artifact: nlm studio delete <nb-id> <artifact-id> --confirm
      (ASK USER FIRST).

Pull references/command_reference.md for artifact-specific flags (formats, lengths, styles, orientations).

Reference Index

FileUse it for
references/command_reference.mdFull CLI command signatures + all options for every nlm command
references/mcp_tools.mdFull MCP tool reference — every mcp__notebooklm-mcp__* tool with parameters
references/workflows.mdEnd-to-end workflow sequences (research → podcast, study materials, Drive sync, batch + cross-notebook)
references/troubleshooting.mdDetailed error recovery — every error, cause, and solution

Quick Reference

nlm --help              # List all commands
nlm <command> --help    # Help for specific command
nlm --ai                # Full AI-optimized documentation
nlm --version           # Check installed version

Rate Limiting

Wait between operations to avoid rate limits:

  • Source operations: 2 seconds
  • Content generation: 5 seconds
  • Research operations: 2 seconds
  • Query operations: 2 seconds

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.