SKILLEMALL.ai
GitHub ↗ RU Sign in

CB nlm-skill

Expert guide for the Gemini Notebook (formerly Google NotebookLM) CLI (`nlm`) and MCP server - interfaces for Gemini Notebook. Use this skill when users want to interact with Gemini Notebook programmatically, including: creating/managing notebooks, checking plan usage and quota windows, adding sources (URLs, YouTube, text, Google Drive), generating content (podcasts, reports, interactive reports, quizzes, flashcards, mind maps, slides, infographics, videos, data tables), conducting research, chatting with sources, or automating Gemini Notebook workflows. Triggers on mentions of "nlm", "notebooklm", "Gemini Notebook", "plan usage", "quota", "podcast generation", "audio overview", "interactive report", "lesson report", "refactor document", "critique draft", or any Gemini Notebook-related automation task.

Not recommendedcritical or high security findings
jacob-bd/notebooklm-mcp-cli Agent Skills author: jacob-bd MIT 8 files body ≈ 15 406 tokens Open the sourcegithub.com↗ analyzed 4 d ago

Expert guide for the Gemini Notebook (formerly Google NotebookLM) CLI (nlm) and MCP server - interfaces for Gemini Notebook.

As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, consistency, execution cost

IntegrationYouTubeGoogle DriveMedia and videoLearningAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
81/100
safety, quality, tests
Safety 60%
81
Quality 40%
81
Run on models
none yet
Process rating
B
65/100
Nearly there
Inputs and preconditions w 11
0
Running it twice w 4
30
Consistency w 8
40
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 2

  • high Exfiltration intent-browser-credential-store SKILL.md:156
    Accesses a browser credential / cookie store
    # Extract cookies from Chrome DevTools and save
Medium and low: 1
  • low Secrets in code secret-high-entropy-token references/workflows.md:91
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    nlm source add <notebook-id> --drive 1KQH…1qq --type doc
    detector

Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 15406 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 65/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 73 mutating operations with no state check
  • 40Consistency. Frontmatter name (nlm-skill) differs from the folder (data)
  • 40Execution cost. Instruction body is 15406 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 29 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 1 branches, has a failure section
  • 100Progress reporting. Reports progress
  • low The response is described with custom markup (105 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 813: 120–800 characters recommended
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 9 example trigger phrases
  • +4Structure: 65 headings
  • +3Step-by-step instructions: 29 items
  • +3Output format is stated explicitly
  • +4Has examples (39 code blocks)
  • +4Reference files are cited in the instructions (6 of 6)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.