marimo-pair
The marimo-pair skill enables an AI agent to interact with a live marimo notebook session. It allows the agent to execute Python code in the notebook's scratchpad, inspect the kernel state, and perform durable edits to the notebook structure using the marimo._code_mode API.
Is marimo-pair safe to install?
Review the source first: our audit of marimo-pair's source files found 2 shell commands, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes arbitrary Python code in a live kernel and runs shell commands to discover or interact with marimo servers. It can modify the notebook structure and state, which may lead to data loss or unintended side effects if not managed correctly.
How we audit skills: our security review methodology.
Who is this skill for?
Developers and data scientists using marimo notebooks who want to automate notebook tasks, pair-program with an AI, or perform programmatic notebook modifications.
What can you do with it?
- Inspecting live notebook variables and dataframes
- Creating new notebook cells programmatically
- Editing existing notebook cells via the marimo._code_mode API
- Managing notebook dependencies through the marimo context
- Updating UI widget values in a running session
How good is this skill?
Quality score: 5/10. The documentation is comprehensive, providing clear instructions on the safe use of the marimo._code_mode API and the risks associated with direct file manipulation. It includes specific examples for common tasks.
What does the skill file contain?
marimo is a reactive Python runtime for building reproducible Python programs (marimo notebooks). Cells are connected by the variables they define and reference. Running a cell re-executes dependents in dataflow order. The active runtime holds the kernel namespace, cell state, and dataflow graph. The notebook (`.py` file) is the artifact the kernel writes from that state while a session is running. A user interacts with the same runtime via a notebook UI with cells, outputs, and widgets. **WARNING. The active runtime is the source of truth.** During a session, you SHOULD NOT modify the assoc...
Frequently asked questions
Should I edit the .py notebook file directly while a session is active?
No. The active runtime is the source of truth. Direct file edits will not reach the active kernel and may be overwritten by the kernel on save.
How do I persist changes to the notebook?
You must use the marimo._code_mode (cm) API. This allows you to create or edit cells and run them within the context of the live kernel.
What is the difference between the scratchpad and the notebook globals?
The scratchpad is a temporary namespace with a shallow copy of kernel globals. Top-level assignments in the scratchpad are discarded after each call, while mutations to existing notebook-owned objects persist.
How do I handle dependencies in a notebook?
Use the ctx.packages.add() or ctx.packages.remove() methods within the marimo context instead of running shell commands like pip or uv.
Related skills
find-skills
2.3MUsers seeking to extend agent capabilities with specialized tools, workflows, or knowledge packages
The find-skills skill enables agents to search for, discover, and install modular packages from the open agent skills ecosystem using the Skills CLI.
video-edit
338.7KUsers of the RunComfy CLI who need to automate video editing tasks like restyling, background swapping, or motion transfer
The video-edit skill acts as a router for the RunComfy CLI, selecting between Wan 2.7 Edit-Video, Kling 2.6 Pro Motion Control, and Lucy Edit Restyle models based on user intent to perform video transformations.
lark-doc
305.2KUsers who need to automate document management, content updates, and media handling within the Lark/Feishu ecosystem
The lark-doc skill enables agents to read, create, and edit Lark (Feishu) documents, including Docx and Wiki formats. It supports content manipulation via XML or Markdown, media handling, and resource management for document covers. The skill integrates with other Lark skills by identifying and delegating operations for embedded objects like spreadsheets, databases, and mind notes.
ai-image-generation
229.9KDevelopers and AI agents requiring programmatic access to diverse image generation and editing models through a unified CLI
The AI Image Generation skill provides a command-line interface for generating and editing images using the RunComfy platform. It routes requests across 11+ AI models, including FLUX 2, Google Nano Banana, OpenAI GPT Image 2, ByteDance Seedream, Alibaba Qwen, and Wan 2-7. The skill selects the appropriate model based on user intent, such as typography precision, photorealism, or speed, and executes the generation via the runcomfy CLI.