notebooklm — Claude Code command: what it does, how to install
notebooklm runs source-grounded research across your Obsidian vault with Gemini File Search. Useful when you need answers tied strictly to personal notes.
MIT ★ 5,412 updated 2026-10-24
/plugin marketplace add eugeniughelbur/obsidian-second-brain
/plugin install obsidian-second-brain@obsidian-second-brainWhat notebooklm does
The command picks 12 matching notes from your vault and sends them to a temporary Gemini File Search store. Gemini processes the bundle and produces a citation-style synthesis. It writes the result straight into Research/NotebookLM/ as a dated Markdown note. The remote file store is cleared immediately afterward.
Next, the workflow triggers entity propagation. Parallel subagents update connected project notes, task files, and contact records based on the findings. It also links the new file inside your current daily note. Without a valid GEMINI_API_KEY saved in ~/.config/obsidian-second-brain/.env, execution will fail.
What it helps with
- synthesize insights grounded strictly in Obsidian vault notes
- propagate research outcomes across related project and task records
- append a link to the generated synthesis in the daily note
- run local document research without opening a web browser
Example prompts for the agent
- /notebooklm microservice migration plan
- /notebooklm quarterly business goals
- /notebooklm customer interview themes
How to install notebooklm
1Plugin marketplace
/plugin marketplace add eugeniughelbur/obsidian-second-brain/plugin install obsidian-second-brain@obsidian-second-brain2Manually: put the files in place
.claude/commands/notebooklm.mdCall it with /notebooklm. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/notebooklm.mdCall it with /prompts:notebooklm. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/notebooklm.prompt.mdManually: put the files in place
.gemini/commands/notebooklm.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about notebooklm
How to install notebooklm in Claude Code?
Run /plugin marketplace add eugeniughelbur/obsidian-second-brain first, then execute /plugin install obsidian-second-brain@obsidian-second-brain.
What does the notebooklm command do?
It retrieves 12 relevant notes from your Obsidian vault, uploads them to Gemini File Search, and generates a grounded synthesis. The command then writes the note to disk and updates related vault entries.
What credentials are required to run this command?
You must set GEMINI_API_KEY inside ~/.config/obsidian-second-brain/.env. By default it uses gemini-2.5-flash, which can be changed with NOTEBOOKLM_MODEL.
Source text
notebooklm.md · MIT
--- description: Vault-first source-grounded research via Gemini File Search. One command, no browser. The grounded parallel to /research-deep (which is open-web via Perplexity). category: research triggers_en: ["notebooklm", "research grounded", "ground research in vault", "ask my notebook", "source-grounded research"] triggers_de: ["NotebookLM", "quellenbasierte Recherche", "Recherche mit meinem Vault", "frag mein Notebook", "Recherche auf Basis meiner Quellen"] triggers_es: ["notebooklm", "investigación fundamentada en mis notas", "basa esto en mi vault", "pregúntale a mis notas", "investigación con fuentes propias", "investiga en mis notas"] triggers_pt: ["notebooklm", "pesquisa ancorada", "ancore a pesquisa no vault", "pergunte ao meu notebook", "pesquisa ancorada em fontes"] triggers_zh: ["用我的资料做研究", "基于知识库回答", "问问我的笔记", "做有来源依据的研究", "用 NotebookLM 研究"] --- Use the obsidian-second-brain skill. Execute `/notebooklm [topic]`: 1. Resolve the topic from the user's argument. If no topic, ask: "What topic for source-grounded research?" 2. Run the script from the skill root (its absolute path was given at session start as **Skill root**; substitute it for `SKILL_ROOT`): ```bash uv run --directory "SKILL_ROOT" -m scripts.research.notebooklm --topic "<topic>" ``` 3. The script does the whole flow end-to-end: - Scans the vault for the top 12 relevant notes (same shape as `/research-deep` Phase 1). - Uploads them to a fresh Gemini File Search store. - Asks Gemini (default `gemini-2.5-flash`, override via `NOTEBOOKLM_MODEL` env) for a synthesis grounded against those sources. - Writes the AI-first synthesis to `Research/NotebookLM/YYYY-MM-DD - <slug>.md`. - Deletes the File Search store so nothing is left behind. - Emits a `<<<NOTEBOOKLM_PROPAGATION_PAYLOAD>>>` JSON block. 4. **After save, do the propagation step.** Same flow as `/research-deep`: - Parse the propagation payload. - Read the saved synthesis at `saved_note`. - Treat the synthesis as the "conversation context" input to `/obsidian-save`. - Run the standard `/obsidian-save` flow: spawn parallel subagents (People, Projects, Tasks, Decisions, Ideas) and update vault notes per any "Recommended next reads or angles" bullets if they map to entities or projects. - Link the new synthesis note from today's daily note. 5. Report back to the user: "Saved [[YYYY-MM-DD - <slug>]] to Research/NotebookLM/. Linked from today's daily note. Updated [[X]], created [[Y]]." 6. Plain English triggers: "notebooklm this", "ground research on X using my vault", "source-grounded research on X", "ask my own notes about X". 7. When to choose `/notebooklm` over `/research-deep`: - `/research-deep` (Perplexity + Grok): when you want OPEN-WEB + X-discourse coverage. Cost: $0.20-0.80. - `/notebooklm` (Gemini File Search): when you want answers GROUNDED IN your own vault. Cost: ~$0.01-0.05. - Run both for high-value topics. The web view and the grounded view rarely contradict, and the contradictions are where the insight is. 8. Configuration: requires `GEMINI_API_KEY` in `~/.config/obsidian-second-brain/.env`. Get one free at https://aistudio.google.com/apikey. Optional `NOTEBOOKLM_MODEL` override (default `gemini-2.5-flash`). --- **AI-first rule:** Every note created or updated by this command MUST follow `references/ai-first-rules.md`. If that path does not resolve from your working directory, search upward for it; if you still cannot read it, say so before writing rather than producing a note that silently skips the rule. The saved synthesis at `Research/NotebookLM/YYYY-MM-DD - <slug>.md` follows the template baked into the script (preamble, frontmatter, vault-baseline links, response verbatim). Do not strip those. **Anti-fabrication:** Search exhaustively before claiming any note, person, or file is absent - false absence is the most common failure mode - and never invent facts, entities, or dates (mark unknowns as `TBD`). See the anti-fabrication and search-completeness hard rules in `references/ai-first-rules.md`. **Why Gemini File Search and not the browser:** NotebookLM has no public API for personal Google accounts. Gemini File Search (generally available, plain API key, same Gemini model family) gives the same architectural shape: source-grounded retrieval, multi-document context, citation-style synthesis. One HTTP call, no manual paste step. **Cost:** $0.15 per million tokens indexed, storage free, generation at standard Gemini token rates. For a 12-note vault bundle (~30K tokens), expect $0.01-0.05 per run.
© Eugeniu Ghelbur · MIT · eugeniughelbur/obsidian-second-brain