Jupyter Notebook

by NousResearch

Jupyter Notebook is a Data skill for Claude Code, published by NousResearch in hermes-agent.

229.7K stars45.3K forkson NousResearch/hermes-agentAdded 2026/08/13Repository updated 2026/08/13

View source on GitHub Download repo ZIP

aiai-agentai-agentsanthropicchatgptclaudeclaude-codecodexhermeshermes-agentllmnous-researchopenai

Install in seconds

Install Jupyter Notebook

Copy Jupyter Notebook into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/NousResearch/hermes-agent/tree/main/optional-skills/data-science/jupyter-notebook ~/.claude/skills/jupyter-notebook

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/NousResearch/hermes-agent.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: optional-skills/data-science/jupyter-notebook/SKILL.md in NousResearch/hermes-agent
Installs to: ~/.claude/skills/jupyter-notebook
Collection: One of 24 skills cataloged from this repository
Category: Data — 668 skills

What Jupyter Notebook does

Jupyter Notebook provides a stateful Python REPL via a live Jupyter kernel (hamelnb) so variables persist across executions. Use it for iterative data exploration, API inspection, and complex code development.

Jupyter Notebook is cataloged under Data on DirSkills. Jupyter Notebook comes from a repository tagged ai, ai-agent, ai-agents, anthropic and chatgpt.

Documentation

README

Excerpt

Jupyter Notebook (hamelnb live kernel)

Gives you a stateful Python REPL via a live Jupyter kernel. Variables persist across executions. Use this instead of execute_code when you need to build up state incrementally, explore APIs, inspect DataFrames, or iterate on complex code.

When to Use This vs Other Tools

Tool	Use When
This skill	Iterative exploration, state across steps, data science, ML, "let me try this and check"
`execute_code`	One-shot scripts needing hermes tool access (web_search, file ops). Stateless.
`terminal`	Shell commands, builds, installs, git, process management

Rule of thumb: If you'd want a Jupyter notebook for the task, use this skill.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Jupyter Notebook

What else does NousResearch publish alongside Jupyter Notebook?
Jupyter Notebook is one of 24 skills that DirSkills catalogs from NousResearch/hermes-agent, the repository it ships in. Its siblings there include 1-3-1 Communication Rule, Antigravity CLI and Article Illustrator. Each one is a separate skill with its own page in this directory, installs the same way Jupyter Notebook does, and is maintained by NousResearch in that same repository. The rest of the collection is listed on the NousResearch/hermes-agent page.
How does Jupyter Notebook compare to other Data skills?
Jupyter Notebook ranks #2 by stars among the 668 Data skills in this catalog. The most-starred ones next to it are Benchmark Methodology, Solana and Hyperliquid. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Jupyter Notebook against them. Open each page to compare what they document and how they install.