agentleFS
azuma520azuma520/youtube-to-notebooklm/skills/anything-to-notebooklm/SKILL.md

anything-to-notebooklm

Skill38 starsChanged 8 months agoMITView on GitHub

Upload content to Google NotebookLM and generate podcasts, slides, mind maps, quizzes, reports, videos, and more. Also browse, search, and query existing notebooks. Supports URLs (web, YouTube), local files (PDF, DOCX, PPTX, XLSX, EPUB, Markdown, images, audio, CSV, JSON, ZIP), AI research, and Google Drive. Use when the user says: "上傳到 NotebookLM", "生成播客", "做成 PPT", "畫思維導圖", "generate podcast", "make slides", "create mind map", "upload to NotebookLM", "做成報告", "出題", "生成 Quiz", "turn this into a podcast", "summarize this as slides", "把這個做成播客", "幫我整理成報告", "ask NotebookLM", "問筆記本", "找之前的筆記本", "NotebookLM 上的", "check my notebooks", "download the podcast", "what notebooks do I have", "搜尋 notebook", "之前的 notebook", "下載播客", "瀏覽筆記本". Activate this skill whenever the user wants to push content to NotebookLM, generate outputs, browse or query existing notebooks, or download previously generated artifacts.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. erafat/skills★ 17same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    NEVER: use source add --wait — this flag does not exist.

    line 142
  2. Very specific:

    NEVER: use --style retro — the correct value is retro-print

    line 144
  3. Very specific:

    NEVER: use 1-based slide index — revise-slide --slide 0 = first slide (zero-based)

    line 145
  4. Distinctive:

    NEVER: create a notebook without confirming the name with the user first

    line 146

≈ “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

多源內容 → NotebookLM 處理器

從多種來源取得內容,上傳到 NotebookLM 生成各類成品;或瀏覽、查詢、提問既有 notebook。

依賴:notebooklm-py(CLI v0.3.3+)、markitdown(僅限 PPTX/XLSX/EPUB 轉換)。首次使用須 notebooklm login。

Decision Tree

用戶請求
├── 想找/瀏覽/查詢/下載既有 notebook 或成品?
│   └── Workflow B:瀏覽 → 閱讀 → 提問
├── 有內容要上傳 / 要生成新東西?
│   └── Workflow A:上傳 → 生成 → 下載
└── 不確定 → 詢問用戶

Workflow A:上傳 → 生成 → 下載

Step 1:識別內容源

輸入特徵處理方式
YouTube URLsource add "URL" → source wait <id>
網頁 URLsource add "URL" → source wait <id>
Google Drive 文件source add-drive <file_id> "title"
本地 .pdf/.docx/.md/.csv/.txtsource add "filepath" → source wait <id>
本地 .pptx/.xlsx/.epubmarkitdown "file" -o "$TEMP/converted.md" → source add
本地圖片/音訊source add "filepath" → source wait <id>(自動 OCR/轉錄)
純關鍵詞source add-research "query"(見下方)

Step 2:建立 notebook + 添加來源

notebooklm create "筆記本標題"
notebooklm source add "來源"          # 上傳來源
notebooklm source wait <source_id>    # 等待處理完成
  • 一個 notebook 最多 50 個 source,全部 source wait 完再生成
  • 上傳前確認:告知用戶即將建立的 notebook 名稱,確認後再執行

Step 3:生成

預設行為是非阻塞(除 mind-map 外)。互動場景加 --wait 等待完成。

用戶意圖指令
播客/音頻generate audio --wait
PPT/簡報generate slide-deck --wait
思維導圖generate mind-map(同步,自動等待)
Quiz/出題generate quiz --wait
報告/總結generate report --wait
視頻generate video --wait
信息圖generate infographic --wait
閃卡generate flashcards --wait
數據表generate data-table "description" --wait

用戶沒指定生成什麼 → 只上傳不生成,等後續指令。

各類型的 format/style/length 參數 → 見 references/generate-options.md。

Step 4:下載

notebooklm download <type> ./output.<ext>

常用選項:--latest(最新成品)、--format <fmt>(輸出格式)、--all(全部下載)。

完整下載選項 → 見 references/generate-options.md。

AI 研究搜尋

用戶給的是純關鍵詞時,用 NotebookLM 內建研究功能:

notebooklm source add-research "query" --mode deep --from web --import-all
notebooklm research wait    # 等待研究完成
  • --mode fast(快速)/ deep(深度)
  • --from web(網路)/ drive(Google Drive)

Workflow B:瀏覽 → 閱讀 → 提問

瀏覽與切換

notebooklm list                              # 列出所有 notebook
notebooklm use <id>                          # 切換(支援部分 ID 匹配)
notebooklm status                            # 當前上下文
notebooklm rename "新名稱"                   # 重新命名

來源管理

notebooklm source list                       # 來源清單
notebooklm source fulltext <id>              # 完整索引文本
notebooklm source guide <id>                 # AI 摘要

提問與對話

notebooklm ask "問題"                        # 對整個 notebook 提問
notebooklm ask "問題" -s <source_id>         # 指定來源提問
notebooklm ask "問題" -c <conversation_id>   # 繼續既有對話
notebooklm ask "問題" --save-as-note --note-title "標題"  # 答案存為筆記

歷史與成品

notebooklm history                           # 對話紀錄
notebooklm summary                           # notebook 摘要
notebooklm artifact list                     # 已生成成品清單
notebooklm note list                         # 筆記清單

分享

notebooklm share public --enable             # 公開分享
notebooklm share add user@email.com          # 邀請特定用戶

NEVER List

  • NEVER use source add --wait — this flag does not exist. Use source wait <id> instead
  • NEVER assume generate blocks — it is async by default (except mind-map). Add --wait for interactive use
  • NEVER use --style retro — the correct value is retro-print
  • NEVER use 1-based slide index — revise-slide --slide 0 = first slide (zero-based)
  • NEVER create a notebook without confirming the name with the user first
  • NEVER assume audio downloads are .wav — the actual format is .mp4 container
  • NEVER poll artifact status in the main conversation for extended periods — use a subagent or inform the user of estimated wait time

整合銜接

  • yt-search:YouTube URL 直接 source add;已有字幕文字檔也可直接 source add
  • markitdown:僅用於 PPTX/XLSX/EPUB(NotebookLM 不直接支援的格式)。PDF/DOCX/MD/CSV/TXT/圖片/音訊直接 source add
  • Obsidian vault:讀取筆記內容後 source add 檔案路徑
  • crawl4ai:反爬蟲網站(X.com 等)先用 crawl4ai 抓取,再 source add 本地檔案

語言設定

notebooklm language set zh_Hant    # 繁體中文
notebooklm language set ja         # 日文

也可在個別指令加 --language zh_Hant。

暫存檔清理

生成完成、用戶確認收到輸出後,清理暫存檔:rm -f "$TEMP"/converted.md


參考資料

需要什麼看哪裡
生成/下載參數明細references/generate-options.md
完整工作流範例references/examples.md
Windows 設定references/windows-setup.md
錯誤排查references/troubleshooting.md

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.