[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69A0W8J3ETTPHACDWGZPDWW":3,"skill-same:01M69A0W8J3ETTPHACDWGZPDWW":77},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M69A0W8J3ETTPHACDWGZPDWW","jupyter-notebook",null,"當使用者要求建立、搭建或編輯 Jupyter 筆記本（`.ipynb`）以進行實驗、探索或教學範例時使用；優先使用隨附的範本，並執行輔助腳本 `new_notebook.py` 來產生一個乾淨的起始筆記本。","microsoft\u002Fai-agents-for-beginners","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M6998ZK2275KMJE6Y5SEA2X2",79423,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-HK\u002F.agents\u002Fskills\u002Fjupyter-notebook\u002FSKILL.md",[],[19],"jupyter notebook","2026-11-10 10:12:30",false,"---\nname: jupyter-notebook\ndescription: 當使用者要求建立、搭建或編輯 Jupyter 筆記本（`.ipynb`）以進行實驗、探索或教學範例時使用；優先使用隨附的範本，並執行輔助腳本\n  `new_notebook.py` 來產生一個乾淨的起始筆記本。\n---\n# Jupyter Notebook 技能\n\n建立清晰、可重現的 Jupyter 筆記本，以兩種主要模式為主：\n\n- 實驗與探索性分析\n- 教學導向的教學步驟\n\n優先使用內建範本與輔助腳本，以維持一致的結構並減少 JSON 錯誤。\n\n## 何時使用\n- 從頭建立新的 `.ipynb` 筆記本。\n- 將草稿筆記或腳本轉換為結構化的筆記本。\n- 重構現有筆記本，使其更具可重現性與易讀性。\n- 建立會被其他人閱讀或重新執行的實驗或教學。\n\n## 決策流程\n- 如果請求屬於探索性、分析性或以假設為驅動，選擇 `experiment`。\n- 如果請求是教學性的、逐步說明或針對特定受眾，選擇 `tutorial`。\n- 如果是編輯現有筆記本，視為重構：保留原意並改善結構。\n\n## 技能路徑（設定一次）\n\n```bash\nexport CODEX_HOME=\"${CODEX_HOME:-$HOME\u002F.codex}\"\nexport JUPYTER_NOTEBOOK_CLI=\"$CODEX_HOME\u002Fskills\u002Fjupyter-notebook\u002Fscripts\u002Fnew_notebook.py\"\n```\n\nUser-scoped skills install under `$CODEX_HOME\u002Fskills` (default: `~\u002F.codex\u002Fskills`).\n\n## 工作流程\n1. Lock the intent.\nIdentify the notebook kind: `experiment` or `tutorial`.\nCapture the objective, audience, and what \"done\" looks like.\n\n2. Scaffold from the template.\nUse the helper script to avoid hand-authoring raw notebook JSON.\n\n```bash\nuv run --python 3.12 python \"$JUPYTER_NOTEBOOK_CLI\" \\\n  --kind experiment \\\n  --title \"Compare prompt variants\" \\\n  --out output\u002Fjupyter-notebook\u002Fcompare-prompt-variants.ipynb\n```\n\n```bash\nuv run --python 3.12 python \"$JUPYTER_NOTEBOOK_CLI\" \\\n  --kind tutorial \\\n  --title \"Intro to embeddings\" \\\n  --out output\u002Fjupyter-notebook\u002Fintro-to-embeddings.ipynb\n```\n\n3. Fill the notebook with small, runnable steps.\nKeep each code cell focused on one step.\nAdd short markdown cells that explain the purpose and expected result.\nAvoid large, noisy outputs when a short summary works.\n\n4. Apply the right pattern.\nFor experiments, follow `references\u002Fexperiment-patterns.md`.\nFor tutorials, follow `references\u002Ftutorial-patterns.md`.\n\n5. Edit safely when working with existing notebooks.\nPreserve the notebook structure; avoid reordering cells unless it improves the top-to-bottom story.\nPrefer targeted edits over full rewrites.\nIf you must edit raw JSON, review `references\u002Fnotebook-structure.md` first.\n\n6. Validate the result.\nRun the notebook top-to-bottom when the environment allows.\nIf execution is not possible, say so explicitly and call out how to validate locally.\nUse the final pass checklist in `references\u002Fquality-checklist.md`.\n\n## 範本與輔助腳本\n- 範本位於 `assets\u002Fexperiment-template.ipynb` 與 `assets\u002Ftutorial-template.ipynb`。\n- 輔助腳本會載入範本、更新標題儲存格，並寫出筆記本。\n\n腳本路徑：\n- `$JUPYTER_NOTEBOOK_CLI` (installed default: `$CODEX_HOME\u002Fskills\u002Fjupyter-notebook\u002Fscripts\u002Fnew_notebook.py`)\n\n## 暫存和輸出慣例\n- 將 `tmp\u002Fjupyter-notebook\u002F` 用作中間檔案；完成後刪除。\n- 在此專案內工作時，將最終產物寫到 `output\u002Fjupyter-notebook\u002F`。\n- 使用穩定且具描述性的檔名（例如，`ablation-temperature.ipynb`）。\n\n## 相依套件（僅在需要時安裝）\n偏好使用 `uv` 來管理相依性。\n\n可選的本地執行筆記本用 Python 套件：\n\n```bash\nuv pip install jupyterlab ipykernel\n```\n\nThe bundled scaffold script uses only the Python standard library and does not require extra dependencies.\n\n## 環境\n不需要任何環境變數。\n\n## 參考清單\n- `references\u002Fexperiment-patterns.md`: 實驗結構與啟發式準則。\n- `references\u002Ftutorial-patterns.md`: 教學結構與教學流程。\n- `references\u002Fnotebook-structure.md`: 筆記本 JSON 結構與安全編輯規則。\n- `references\u002Fquality-checklist.md`: 最終驗證清單。\n\n---\n\n\u003C!-- CO-OP TRANSLATOR DISCLAIMER START -->\n免責聲明：\n本文件由 AI 翻譯服務 [Co-op Translator](https:\u002F\u002Fgithub.com\u002FAzure\u002Fco-op-translator) 翻譯。雖然我們力求準確，但請注意，自動翻譯可能包含錯誤或不準確之處。以原始語言撰寫的原文應被視為具權威性的版本。對於重要資訊，建議採用專業人工翻譯。我們對因使用本翻譯而導致的任何誤解或錯誤詮釋概不負責。\n\u003C!-- CO-OP TRANSLATOR DISCLAIMER END -->","# Jupyter Notebook 技能\n\n建立清晰、可重現的 Jupyter 筆記本，以兩種主要模式為主：\n\n- 實驗與探索性分析\n- 教學導向的教學步驟\n\n優先使用內建範本與輔助腳本，以維持一致的結構並減少 JSON 錯誤。\n\n## 何時使用\n- 從頭建立新的 `.ipynb` 筆記本。\n- 將草稿筆記或腳本轉換為結構化的筆記本。\n- 重構現有筆記本，使其更具可重現性與易讀性。\n- 建立會被其他人閱讀或重新執行的實驗或教學。\n\n## 決策流程\n- 如果請求屬於探索性、分析性或以假設為驅動，選擇 `experiment`。\n- 如果請求是教學性的、逐步說明或針對特定受眾，選擇 `tutorial`。\n- 如果是編輯現有筆記本，視為重構：保留原意並改善結構。\n\n## 技能路徑（設定一次）\n\n```bash\nexport CODEX_HOME=\"${CODEX_HOME:-$HOME\u002F.codex}\"\nexport JUPYTER_NOTEBOOK_CLI=\"$CODEX_HOME\u002Fskills\u002Fjupyter-notebook\u002Fscripts\u002Fnew_notebook.py\"\n```\n\nUser-scoped skills install under `$CODEX_HOME\u002Fskills` (default: `~\u002F.codex\u002Fskills`).\n\n## 工作流程\n1. Lock the intent.\nIdentify the notebook kind: `experiment` or `tutorial`.\nCapture the objective, audience, and what \"done\" looks like.\n\n2. Scaffold from the template.\nUse the helper script to avoid hand-authoring raw notebook JSON.\n\n```bash\nuv run --python 3.12 python \"$JUPYTER_NOTEBOOK_CLI\" \\\n  --kind experiment \\\n  --title \"Compare prompt variants\" \\\n  --out output\u002Fjupyter-notebook\u002Fcompare-prompt-variants.ipynb\n```\n\n```bash\nuv run --python 3.12 python \"$JUPYTER_NOTEBOOK_CLI\" \\\n  --kind tutorial \\\n  --title \"Intro to embeddings\" \\\n  --out output\u002Fjupyter-notebook\u002Fintro-to-embeddings.ipynb\n```\n\n3. Fill the notebook with small, runnable steps.\nKeep each code cell focused on one step.\nAdd short markdown cells that explain the purpose and expected result.\nAvoid large, noisy outputs when a short summary works.\n\n4. Apply the right pattern.\nFor experiments, follow `references\u002Fexperiment-patterns.md`.\nFor tutorials, follow `references\u002Ftutorial-patterns.md`.\n\n5. Edit safely when working with existing notebooks.\nPreserve the notebook structure; avoid reordering cells unless it improves the top-to-bottom story.\nPrefer targeted edits over full rewrites.\nIf you must edit raw JSON, review `references\u002Fnotebook-structure.md` first.\n\n6. Validate the result.\nRun the notebook top-to-bottom when the environment allows.\nIf execution is not possible, say so explicitly and call out how to validate locally.\nUse the final pass checklist in `references\u002Fquality-checklist.md`.\n\n## 範本與輔助腳本\n- 範本位於 `assets\u002Fexperiment-template.ipynb` 與 `assets\u002Ftutorial-template.ipynb`。\n- 輔助腳本會載入範本、更新標題儲存格，並寫出筆記本。\n\n腳本路徑：\n- `$JUPYTER_NOTEBOOK_CLI` (installed default: `$CODEX_HOME\u002Fskills\u002Fjupyter-notebook\u002Fscripts\u002Fnew_notebook.py`)\n\n## 暫存和輸出慣例\n- 將 `tmp\u002Fjupyter-notebook\u002F` 用作中間檔案；完成後刪除。\n- 在此專案內工作時，將最終產物寫到 `output\u002Fjupyter-notebook\u002F`。\n- 使用穩定且具描述性的檔名（例如，`ablation-temperature.ipynb`）。\n\n## 相依套件（僅在需要時安裝）\n偏好使用 `uv` 來管理相依性。\n\n可選的本地執行筆記本用 Python 套件：\n\n```bash\nuv pip install jupyterlab ipykernel\n```\n\nThe bundled scaffold script uses only the Python standard library and does not require extra dependencies.\n\n## 環境\n不需要任何環境變數。\n\n## 參考清單\n- `references\u002Fexperiment-patterns.md`: 實驗結構與啟發式準則。\n- `references\u002Ftutorial-patterns.md`: 教學結構與教學流程。\n- `references\u002Fnotebook-structure.md`: 筆記本 JSON 結構與安全編輯規則。\n- `references\u002Fquality-checklist.md`: 最終驗證清單。\n\n---\n\n\u003C!-- CO-OP TRANSLATOR DISCLAIMER START -->\n免責聲明：\n本文件由 AI 翻譯服務 [Co-op Translator](https:\u002F\u002Fgithub.com\u002FAzure\u002Fco-op-translator) 翻譯。雖然我們力求準確，但請注意，自動翻譯可能包含錯誤或不準確之處。以原始語言撰寫的原文應被視為具權威性的版本。對於重要資訊，建議採用專業人工翻譯。我們對因使用本翻譯而導致的任何誤解或錯誤詮釋概不負責。\n\u003C!-- CO-OP TRANSLATOR DISCLAIMER END -->",{"name":5,"description":7},"main","f09e94ffe170f8af6d3db7c42987bbe4db227723","translations\u002Fzh-HK\u002F.agents\u002Fskills\u002Fjupyter-notebook",26019,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners","https:\u002F\u002Faka.ms\u002Fai-agents-beginners","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-07 12:51:12",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add microsoft\u002Fai-agents-for-beginners --skill jupyter-notebook",{"tool":41,"command":42},"bunx","bunx skills add microsoft\u002Fai-agents-for-beginners --skill jupyter-notebook",{"tool":44,"command":45},"pnpm","pnpm dlx skills add microsoft\u002Fai-agents-for-beginners --skill jupyter-notebook","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-HK\u002F.agents\u002Fskills\u002Fjupyter-notebook\u002FSKILL.md",true,[49,55,59,65,69,73],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"assets\u002Fexperiment-template.ipynb","ASSET","资产文件",2815,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-HK\u002F.agents\u002Fskills\u002Fjupyter-notebook\u002Fassets\u002Fexperiment-template.ipynb",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"assets\u002Ftutorial-template.ipynb",2758,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-HK\u002F.agents\u002Fskills\u002Fjupyter-notebook\u002Fassets\u002Ftutorial-template.ipynb",{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fexperiment-patterns.md","REFERENCE","参考文档",1188,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-HK\u002F.agents\u002Fskills\u002Fjupyter-notebook\u002Freferences\u002Fexperiment-patterns.md",{"path":66,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fnotebook-structure.md",1283,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-HK\u002F.agents\u002Fskills\u002Fjupyter-notebook\u002Freferences\u002Fnotebook-structure.md",{"path":70,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fquality-checklist.md",1096,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-HK\u002F.agents\u002Fskills\u002Fjupyter-notebook\u002Freferences\u002Fquality-checklist.md",{"path":74,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Ftutorial-patterns.md",1179,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-HK\u002F.agents\u002Fskills\u002Fjupyter-notebook\u002Freferences\u002Ftutorial-patterns.md",[78,96,107,115,121,128],{"skillNo":79,"name":80,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":93,"publishedAt":20},"01M69A206TRZ8KK0CW0HYJF5V5","testing-course-samples","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-TW\u002F.agents\u002Fskills\u002Ftesting-course-samples\u002FSKILL.md",[83,88],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000039","教师与教育","PROFESSION","适用职业",[94,95],"testing","testing course samples",{"skillNo":97,"name":98,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":104,"publishedAt":20},"01M69A1XRB2SFHYRMEH0K08EKZ","microsoft-docs","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-TW\u002F.agents\u002Fskills\u002Fmicrosoft-docs\u002FSKILL.md",[101],{"categoryNo":102,"categoryName":103,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000023","Skill与智能体开发",[105,9,106],"docs","microsoft docs",{"skillNo":108,"name":109,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":20},"01M69A1VPZFJQ1HNGTZQ5P3WSC","local-ai-agents","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-TW\u002F.agents\u002Fskills\u002Flocal-ai-agents\u002FSKILL.md",[],[113,114],"ai agents","local ai agents",{"skillNo":116,"name":5,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":20},"01M69A1S947N7MM6V9JF85S2E7","當使用者要求建立、搭建或編輯 Jupyter 筆記本（`.ipynb`）用於實驗、探索或教學時使用；優先使用隨附範本並執行輔助腳本 `new_notebook.py` 來產生一個乾淨的起始筆記本。","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-TW\u002F.agents\u002Fskills\u002Fjupyter-notebook\u002FSKILL.md",[],[19],{"skillNo":122,"name":123,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":20},"01M69A1Q8EXPWKZSQK69V6WF22","deploying-scalable-agents","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-TW\u002F.agents\u002Fskills\u002Fdeploying-scalable-agents\u002FSKILL.md",[],[127],"deploying scalable agents",{"skillNo":129,"name":130,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":20},"01M69A1MHZTH3RH9N8VYSYG74X","azure-openai-to-responses","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fai-agents-for-beginners\u002Fblob\u002Fmain\u002Ftranslations\u002Fzh-TW\u002F.agents\u002Fskills\u002Fazure-openai-to-responses\u002FSKILL.md",[],[134],"azure openai to responses"]