Menu
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。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Shift Python apps dem from Azure OpenAI Chat Completions go Responses API. E cover AzureOpenAI/AsyncAzureOpenAI client shift go v1 endpoint, streaming, tools, structured output, multi-turn, EntraID auth, plus model compatibility checks. Na Python-focused, Azure OpenAI-specific. USE FOR: shift go responses API, change from chat completions, openai responses, upgrade openai SDK, responses API migration, move from completions go responses, gpt-5 migration, azure openai python migration, chat completions go responses, AzureOpenAI go OpenAI client, python azure openai upgrade. DO NOT USE FOR: build new apps from scratch (start with responses directly), Node/TypeScript/C#/Java/Go migrations (dis skill na Python-only), Azure infrastructure setup (use azure-prepare), deploy models (use microsoft-foundry).
Take one working agent prototype go scalable, observable production deployment for Microsoft Foundry. E cover deployment patterns (client-hosted, hosted agents, agent workflows), the agent lifecycle, model routing, response caching, evaluation gates, human-in-the-loop approval, observability with OpenTelemetry, cost optimisation, and smoke-testing deployed agents with the AI Smoke Test action. Based on Lesson 16 of AI Agents for Beginners. USE FOR: deploy one agent go production, scale one agent, Microsoft Foundry hosted agent, Foundry Agent Service, model routing, response caching, evaluation gate, release gate, human approval workflow, agent observability, agent tracing, agent cost optimisation, smoke test one hosted agent, production customer support agent. DO NOT USE FOR: building your first agent (start with Lesson 01), running agents locally on-device (use local-ai-agents / Lesson 17), Azure infrastructure provisioning we no relate to agents, non-Foundry deployment targets.
Build local-first AI agents wey dey run fully for developer workstation wit Microsoft Foundry Local and Qwen function-calling models. E cover Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG wit Chroma, local MCP servers, hybrid cloud/local routing, and di privacy/cost/offline trade-offs. E based on Lesson 17 of AI Agents for Beginners. USE FOR: run agent locally, offline agent, on-device agent, Foundry Local, Qwen function calling, local tool calling, local RAG, Chroma vector database, local MCP server, privacy-preserving agent, hybrid local and cloud agent, small language model agent, engineering assistant for my machine. DO NOT USE FOR: deploying agents to di cloud at scale (use deploying-scalable-agents / Lesson 16), building your first agent concept (Lesson 01), Foundry (cloud) hosted agents, GPU cluster / server-side inference provisioning.
Use wen dem ask to check, test, do smoke-test, or run di course notebook and code samples against live Microsoft Foundry / Azure OpenAI setup. E cover how to set environment (.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).
Migrate Python apps from Azure OpenAI Chat Completions to the Responses API. Covers AzureOpenAI/AsyncAzureOpenAI client migration to the v1 endpoint, streaming, tools, structured output, multi-turn, EntraID auth, and model compatibility checks. Python-focused, Azure OpenAI-specific. USE FOR: migrate to responses API, switch from chat completions, openai responses, upgrade openai SDK, responses API migration, move from completions to responses, gpt-5 migration, azure openai python migration, chat completions to responses, AzureOpenAI to OpenAI client, python azure openai upgrade. DO NOT USE FOR: building new apps from scratch (start with responses directly), Node/TypeScript/C#/Java/Go migrations (this skill is Python-only), Azure infrastructure setup (use azure-prepare), deploying models (use microsoft-foundry).
| 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。