j-cli

Control Jupyter servers and kernels from the CLI with JSON output.

5|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/TTTPOB/jcli --skill j-cli
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: j-cli
Source: https://github.com/TTTPOB/jcli/tree/main/skills/j-cli
Command: npx skills add https://github.com/TTTPOB/jcli --skill j-cli

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill enables AI agents and developers to control Jupyter servers and notebooks from the command line, execute code on kernels, manage sessions and kernels, and synchronize outputs back to notebooks without manual switching between tools.

Core Features & Use Cases

  • Remote control of Jupyter servers and kernels from the CLI, including creating, listing, interrupting, and restarting sessions.
  • Execute code inline or from notebooks and py:percent scripts, with automatic notebook writeback of outputs.
  • Inspect kernel state and search notebook content with ripgrep, enabling quick debugging and content discovery.

Quick Start

Connect to a Jupyter server with j-cli healthcheck, then create a session and execute cells from notebook.ipynb.

Frequently Asked Questions about j-cli

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I control Jupyter servers and kernels from the command line?

Control Jupyter servers and kernels from the CLI by managing session lifecycles, executing code, and handling kernel operations. The workflow provides command-line execution with JSON output and structured error handling.

Can I execute code from a py:percent script and write outputs back to a notebook?

Yes, you can execute code inline or from py:percent scripts and notebooks. The execution automatically handles notebook writeback, synchronizing outputs directly back to the notebook files.

How do I manage Jupyter sessions and inspect kernel state remotely?

Manage Jupyter sessions remotely by creating, listing, interrupting, and restarting them via the CLI. You can also inspect kernel state and run healthchecks to verify server connectivity and status.

What is the best way to search notebook content for debugging without opening the UI?

Search notebook content directly from the CLI using integrated ripgrep support. This enables quick debugging and content discovery across notebooks without needing to open the graphical interface.

Does this CLI approach suit AI agents needing remote code execution?

Yes, this CLI approach is designed for AI agents and developers needing remote execution. It provides command-line workflows, session management, and structured JSON output for automated processing.

Why use a CLI tool for Jupyter notebook editing instead of the standard web interface?

Using a CLI tool for Jupyter notebook editing removes the need to manually switch between tools. It enables automated code execution, py:percent script editing, and output synchronization directly in the terminal.