Run Agent-Assisted Notebook Workflows in JupyterLab With Notebook Intelligence
Use Notebook Intelligence to add chat, inline edit, autocomplete, MCP tools, Claude Code mode, and coding-agent launchers directly inside JupyterLab.
npx skills add agentskillexchange/skills --skill run-agent-assisted-notebook-workflows-in-jupyterlab-with-notebook-intelligence
Notebook Intelligence is a JupyterLab extension for agent-assisted notebook work. The operator installs the extension, opens the NBI panel in JupyterLab, connects GitHub Copilot, an OpenAI-compatible endpoint, LiteLLM, Ollama, or Claude mode, then uses chat, inline edits, autocomplete, MCP tools, rulesets, and coding-agent launcher tiles while working inside notebooks.
What this skill actually does
Use this instead of using a separate chat product or terminal agent when the work is centered on notebooks and the agent needs notebook-aware context, cell execution, file edits, Jupyter UI tools, or Claude Code sessions opened from the current JupyterLab directory. It fits data-science, research, teaching, and exploratory coding workflows where notebook state matters.
The scope boundary is notebook-native agent assistance inside JupyterLab. It is not a generic Jupyter extension listing, not a model provider card, and not a broad framework. The approved workflow is bringing an existing agent/provider surface into notebook authoring, execution, MCP tooling, and review without leaving the notebook workspace.