重要前提
安装AI Skills的关键前提是:必须科学上网,且开启TUN模式,这一点至关重要,直接决定安装能否顺利完成,在此郑重提醒三遍:科学上网,科学上网,科学上网。查看完整安装教程 →
jupyter-notebook by davila7/claude-code-templates
npx skills add https://github.com/davila7/claude-code-templates --skill jupyter-notebook创建简洁、可复现的 Jupyter 笔记本,主要适用于两种模式:
建议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"
用户作用域内的技能安装在 $CODEX_HOME/skills 下(默认:)。
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
~/.codex/skillsexperiment 或 tutorial。明确目标、受众以及“完成”的标准。uv run --python 3.12 python "$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
3. 用小型、可运行的步骤填充笔记本。保持每个代码单元格专注于一个步骤。添加简短的 Markdown 单元格来解释目的和预期结果。如果简短的总结就足够,避免冗长、杂乱的输出。
4. 应用正确的模式。对于实验,遵循 references/experiment-patterns.md。对于教程,遵循 references/tutorial-patterns.md。
5. 处理现有笔记本时安全地进行编辑。保留笔记本结构;除非能改善自上而下的叙事逻辑,否则避免重新排序单元格。优先进行有针对性的编辑,而不是完全重写。如果必须编辑原始 JSON,请先查看 references/notebook-structure.md。
6. 验证结果。在环境允许的情况下,从头到尾运行笔记本。如果无法执行,请明确说明并指出如何在本地进行验证。使用 references/quality-checklist.md 中的最终检查清单。
assets/experiment-template.ipynb 和 assets/tutorial-template.ipynb。脚本路径:
$JUPYTER_NOTEBOOK_CLI(安装默认路径:$CODEX_HOME/skills/jupyter-notebook/scripts/new_notebook.py)tmp/jupyter-notebook/ 存放中间文件;完成后删除。output/jupyter-notebook/ 下。ablation-temperature.ipynb)。优先使用 uv 进行依赖管理。
用于本地笔记本执行的可选 Python 包:
uv pip install jupyterlab ipykernel
捆绑的脚手架脚本仅使用 Python 标准库,不需要额外的依赖项。
无需必需的环境变量。
references/experiment-patterns.md:实验结构和启发式方法。references/tutorial-patterns.md:教程结构和教学流程。references/notebook-structure.md:笔记本 JSON 结构和安全编辑规则。references/quality-checklist.md:最终验证检查清单。每周安装次数
46
仓库
GitHub 星标数
22.6K
首次出现
2026年2月11日
安全审计
安装于
opencode46
gemini-cli46
github-copilot46
codex46
amp46
kimi-cli46
Create clean, reproducible Jupyter notebooks for two primary modes:
Prefer the bundled templates and the helper script for consistent structure and fewer JSON mistakes.
.ipynb notebook from scratch.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 $CODEX_HOME/skills (default: ~/.codex/skills).
Lock the intent. Identify the notebook kind: experiment or tutorial. Capture the objective, audience, and what "done" looks like.
Scaffold from the template. Use the helper script to avoid hand-authoring raw notebook JSON.
uv run --python 3.12 python "$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
3. Fill the notebook with small, runnable steps. 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.
Apply the right pattern. For experiments, follow references/experiment-patterns.md. For tutorials, follow references/tutorial-patterns.md.
Edit safely when working with existing notebooks. 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.
Validate the result. 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 and assets/tutorial-template.ipynb.Script path:
$JUPYTER_NOTEBOOK_CLI (installed default: $CODEX_HOME/skills/jupyter-notebook/scripts/new_notebook.py)tmp/jupyter-notebook/ for intermediate files; delete when done.output/jupyter-notebook/ when working in this repo.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: experiment structure and heuristics.references/tutorial-patterns.md: tutorial structure and teaching flow.references/notebook-structure.md: notebook JSON shape and safe editing rules.references/quality-checklist.md: final validation checklist.Weekly Installs
46
Repository
GitHub Stars
22.6K
First Seen
Feb 11, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
opencode46
gemini-cli46
github-copilot46
codex46
amp46
kimi-cli46
前端代码审计工具 - 自动化检测可访问性、性能、响应式设计、主题化与反模式
57,700 周安装
Azure Event Hub Python 客户端库 - 实时数据流处理与云消息队列解决方案
1 周安装
Azure Event Grid .NET SDK - 事件驱动架构与云服务集成开发工具
1 周安装
PDForge API (PDF Noodle) - 从HTML/模板生成PDF和PNG的API服务
62 周安装
Azure Data Tables Python 技能包 - 高效管理 Azure 表存储数据
1 周安装
Azure Cosmos Java SDK 技能包 - 高效开发云原生数据库应用
1 周安装
Azure Cosmos DB Python SDK 技能包 - 云端NoSQL数据库开发与集成指南
1 周安装