菜单
在用户请求为实验、探索或教程创建、搭建或编辑 Jupyter 笔记本（`.ipynb`）时使用；优先使用捆绑的模板并运行辅助脚本 `new_notebook.py` 来生成一个干净的起始笔记本。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Tumia wakati unapoombwa kuthibitisha, kujaribu, kufanya mtihani wa haraka, au kuendesha daftari la kozi na mifano ya msimbo dhidi ya usanidi hai wa Microsoft Foundry / Azure OpenAI. Inajumuisha usanidi wa mazingira (.env, az login, vifurushi), mchezaji wa scripts/validate-notebooks.ps1, kutafsiri matokeo ya PASS/FAIL, na ni masomo yapi yanayohitaji rasilimali za ziada (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
Použite, keď sa vyžaduje overenie, testovanie, rýchle testovanie alebo spustenie poznámkového bloku kurzu a ukážok kódu proti živej konfigurácii Microsoft Foundry / Azure OpenAI. Pokrýva nastavenie prostredia (.env, az login, balíky), skript runner scripts/validate-notebooks.ps1, interpretáciu výsledkov PASS/FAIL a ktoré lekcie potrebujú ďalšie zdroje (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
Brukes når du blir bedt om å validere, teste, røykteste eller kjøre kursets notatbok og kodeeksempler mot en aktiv Microsoft Foundry / Azure OpenAI-konfigurasjon. Dekker miljøoppsett (.env, az login, pakker), skriptet/validate-notebooks.ps1-kjøreren, tolkning av PASS/FAIL-resultater, og hvilke leksjoner som trenger ekstra ressurser (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
Gamitin kapag hiniling na i-validate, subukan, smoke-test, o patakbuhin ang notebook ng kurso at mga halimbawa ng code laban sa isang live na Microsoft Foundry / Azure OpenAI na configuration. Saklaw nito ang pag-setup ng kapaligiran (.env, az login, mga package), ang scripts/validate-notebooks.ps1 runner, ang pagpapakahulugan ng mga resulta na PASS/FAIL, at kung aling mga aralin ang nangangailangan ng karagdagang mga mapagkukunan (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
Use wen dem ask you to validate, test, smoke-test, or run di course notebook and code samples against live Microsoft Foundry / Azure OpenAI configuration. E cover environment setup (.env, az login, packages), di scripts/validate-notebooks.ps1 runner, how to understand PASS/FAIL results, and which lessons need extra resources (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
Use when asked to validate, test, smoke-test, or run the course's notebook and code samples against a live Microsoft Foundry / Azure OpenAI configuration. Covers environment setup (.env, az login, packages), the scripts/validate-notebooks.ps1 runner, interpreting PASS/FAIL results, and which lessons need extra resources (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
| name | jupyter-notebook |
| description | 在用户请求为实验、探索或教程创建、搭建或编辑 Jupyter 笔记本（`.ipynb`）时使用；优先使用捆绑的模板并运行辅助脚本 `new_notebook.py` 来生成一个干净的起始笔记本。 |
为两种主要模式创建简洁、可重现的 Jupyter 笔记本：
优先使用捆绑的模板和辅助脚本，以获得一致的结构并减少 JSON 错误。
.ipynb 笔记本。experiment。tutorial。export CODEX_HOME="${CODEX_HOME:-$HOME/.codex}"
export JUPYTER_NOTEBOOK_CLI="$CODEX_HOME/skills/jupyter-notebook/scripts/new_notebook.py"
User-scoped skills install under $CODEX_HOME/skills (default: ~/.codex/skills).
确定意图。
Identify the notebook kind: experiment or tutorial.
Capture the objective, audience, and what "done" looks like.
从模板搭建脚手架。 Use the helper script to avoid hand-authoring raw notebook JSON.
uv run --python 3.12 python "$JUPYTER_NOTEBOOK_CLI" \
--kind experiment \
--title "Compare prompt variants" \
--out output/jupyter-notebook/compare-prompt-variants.ipynb
uv run --python 3.12 python "$JUPYTER_NOTEBOOK_CLI" \
--kind tutorial \
--title "Intro to embeddings" \
--out output/jupyter-notebook/intro-to-embeddings.ipynb
用小的、可运行的步骤填充笔记本。 Keep each code cell focused on one step. Add short markdown cells that explain the purpose and expected result. Avoid large, noisy outputs when a short summary works.
应用合适的模式。
For experiments, follow references/experiment-patterns.md.
For tutorials, follow references/tutorial-patterns.md.
在处理现有笔记本时安全编辑。
Preserve the notebook structure; avoid reordering cells unless it improves the top-to-bottom story.
Prefer targeted edits over full rewrites.
If you must edit raw JSON, review references/notebook-structure.md first.
验证结果。
Run the notebook top-to-bottom when the environment allows.
If execution is not possible, say so explicitly and call out how to validate locally.
Use the final pass checklist in references/quality-checklist.md.
assets/experiment-template.ipynb 和 assets/tutorial-template.ipynb。脚本路径：
$JUPYTER_NOTEBOOK_CLI (安装默认: $CODEX_HOME/skills/jupyter-notebook/scripts/new_notebook.py)tmp/jupyter-notebook/；完成后删除。output/jupyter-notebook/。ablation-temperature.ipynb）。Prefer uv for dependency management.
Optional Python packages for local notebook execution:
uv pip install jupyterlab ipykernel
The bundled scaffold script uses only the Python standard library and does not require extra dependencies.
No required environment variables.
references/experiment-patterns.md: 实验结构与启发式准则。references/tutorial-patterns.md: 教程结构与教学流程。references/notebook-structure.md: 笔记本 JSON 结构与安全编辑规则。references/quality-checklist.md: 最终验证检查清单。免责声明： 本文件已使用 AI 翻译服务 Co-op Translator 进行翻译。虽然我们努力保证准确性，但自动翻译可能存在错误或不准确之处。应以原文（原始语言版本）为准。对于重要信息，建议采用专业人工翻译。由于使用本翻译而导致的任何误解或误释，我们概不负责。