- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add roomi-fields/notebooklm-mcp --skill notebooklm -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add roomi-fields/notebooklm-mcp --skill notebooklm -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add roomi-fields/notebooklm-mcp --skill notebooklm -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add roomi-fields/notebooklm-mcp --skill notebooklm -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/roomi-fields/notebooklm-mcp/tree/HEAD/skills/notebooklm來自發布者
NotebookLM answers questions only from the sources uploaded to a notebook,
with inline citations to the exact passages used — no open-web knowledge, so
answers are hallucination-resistant and fully traceable. This skill drives the
@roomi-fields/notebooklm-mcp engine to query notebooks, manage sources, and
generate Studio content, and encodes the patterns that make NotebookLM usable at
research scale (citation formats, the ~50-queries/day quota, batch-to-cache).
Two ways reach the same engine — pick per what the session already has:
notebook_ask / source_add /
server_health (or mcp__notebooklm__*) are available in the session, call
them directly. This is the preferred path and needs no server.scripts/nblm.sh, which talks
to a running NotebookLM MCP server (default http://localhost:3000,
override with NOTEBOOKLM_SERVER_URL). If no server is reachable, ask the
user to start one (npm run start:http from a clone) or to install the MCP.Both are backed by the same account and session, so the choice is purely about which is already wired up.
NotebookLM needs a signed-in Google session (saved once, reused across runs).
Verify with nblm.sh health (or the server_health tool) — look for
authenticated: true. If not authenticated, run the interactive login in a
terminal (a visible Chrome window opens):
notebooklm-mcp-setup-auth # global install
# or: scripts/nblm.sh auth
Run the login in a terminal rather than through an in-client tool: interactive Google login can take minutes and a stdio client's tool-call timeout may cut it off.
Use scripts/nblm.sh for the REST path (or the equivalent MCP tool):
scripts/nblm.sh health # reachability + auth status
scripts/nblm.sh notebooks # list notebooks (id + name)
scripts/nblm.sh ask "<question>" <notebook_id> # citation-backed answer (JSON citations)
scripts/nblm.sh search "<query>" <notebook_id> [limit] # ranked passages, no answer, no quota
scripts/nblm.sh generate <notebook_id> report # audio|report|video|infographic|presentation|data_table|flashcards|quiz|mind_map
search returns the indexed passages matching a
query, ranked best first, and spends no chat quota because nothing is
generated. When you intend to reason over the evidence yourself, it is both
cheaper and faster than asking. Rank is global across sources and lower is
better; start/end are offsets into that source's full text, and are null
when the server gave none.source_format: json, so the answer carries
source names + cited excerpts. For a human-facing answer, prefer expanded
(see references/rest-api.md to vary the format).flashcards/quiz route to the study-aid endpoint and
mind_map to the mind-map endpoint automatically.For anything beyond a few questions, load references/research-workflows.md. Key
points:
/re-auth) or, better, ingest once and retrieve offline./batch-to-vault (writes markdown + nblm-answer-v1 JSON
sidecars with citations), then answer repeated questions from the cache
(e.g. with RTFM) — unlimited, offline.session_id for independent questions (fastest);
pass a stable one to continue a conversation.references/rest-api.md — endpoint + body reference for the HTTP path.references/research-workflows.md — citation formats, quota strategy, the
batch/ingestion pattern, source discovery.If neither the MCP tools nor a server are present, the engine is the npm package
@roomi-fields/notebooklm-mcp
(also a Claude Code plugin via the roomi-fields/claude-plugins marketplace).
Point the user there, then run the one-time login above.
This skill should be used when the user wants to query their Google NotebookLM notebooks for citation-backed, source-grounded answers, or manage notebooks, sources, and Studio content (audio, report,
---name: notebooklmdescription: This skill should be used when the user wants to query their Google NotebookLM notebooks for citation-backed…---# skills/notebooklm/SKILL.md總覽
This skill should be used when the user wants to query their Google NotebookLM notebooks for citation-backed, source-grounded answers, or manage notebooks, sources, and Studio content (audio, report, video, infographic, presentation, data table, flashcards, quiz, mind map). It drives the @roomi-fields/notebooklm-mcp engine — via the notebooklm MCP tools when they are available in the session, otherwise via its HTTP REST API — and covers Google login, citation formats, the daily-quota-aware batch/ingestion pattern, and source discovery.
常見問題
從發布者下載 skills/notebooklm/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/roomi-fields/notebooklm-mcp。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。