← ClaudeAtlas

research-notebooklisted

Deep research on any topic via the NotebookLM CLI. Use whenever the user requests research on a topic, in any project, in any language. Triggers on phrases like "research this", "deep dive on", "do research on", "dig into", "find out about", "investigate", "look into", "research X for me". Creates or reuses a NotebookLM notebook, ingests 5–10 fresh sources, asks structured questions, and returns a cited synthesis. For multi-faceted topics, signals the main thread to fan out parallel sub-agents (web + hub + qmd) alongside.
ManceRayder42/jarvis-os · ★ 4 · AI & Automation · score 80
Install: claude install-skill ManceRayder42/jarvis-os
# research-notebook — NotebookLM-Powered Research Skill Routes any research request through the user's local `notebooklm` CLI so collected sources, summaries, and Q&A become a durable, queryable artifact rather than scrollback. ## Prerequisite This skill assumes the `notebooklm` CLI is installed and authenticated (Google account) separately — it is not bundled with this plugin. If `notebooklm list` fails outright, tell the user it needs installing/logging in rather than silently falling back to plain web search. ## When to use - User asks to research, investigate, or dig into a topic (any language). - User compares options, evaluates a tool, asks "what's the best way to do X", or wants a strategic overview. - Single-shot factual lookups that would benefit from cited sources (e.g. "find out about Vercel Edge limits in 2026"). ## When NOT to use - Trivial single-fact answers the model already knows confidently and the user just wants in chat. - Questions about the user's own hub/notes — that's the `qmd` skill, if installed. - An already-existing project-specific research workflow the user has of their own. - Pure code questions answerable by reading the repo. ## Workflow ### Step 1 — Extract the topic Pull 1–5 keywords from the user message. If the topic is unclear or too broad to act on, ask ONE clarifying question before continuing. Preserve the user's language. ### Step 2 — Check for an existing notebook FIRST ```bash notebooklm list ``` Fuzzy-match the topic again