Agent skill · writing content · nousresearch
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
Why this skill is useful
Provides specific commands and workflows for managing Jupyter notebooks that enhance the AI's ability to perform iterative data science tasks.
What it needs
Requires jupyterlab, uv installed locally. About 3k tokens when loaded. Last updated 2026-08-07. 226,679 stars on the source repository.
What this skill does
Jupyter Notebook (hamelnb live kernel) Gives you a stateful Python REPL via a live Jupyter kernel. Variables persist across executions. Use this instead of executecode 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" executecode One-shot scripts needing hermes tool access (websearch, 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. Prerequisites 1. uv must be installed (check: which uv) 2. JupyterLab must be installed: uv tool install jupyterlab 3. A Jupyter server must be running (see Setup below) Setup The hamelnb script location: If not cloned yet: Starting JupyterLab Check if a server is already running: If no servers found, start one: Note: Token/password disabled for local agent access. The server runs headless. Creating a Notebook for REPL Use If you just need a REPL (no existing notebook), create a minimal notebook file: Write a minimal .ipynb JSON file with one empty code cell, then start a kernel session via the Jupyter REST API: Core Workflow All commands return structured JSON. Always use --compact to save tokens. 1. Discover servers and notebooks 2. Execute code (primary operation) State persists across execute calls. Variables, imports, objects all survive. Multi-line code works with