Convert notebooks into reactive marimo .py files with uv sandboxing.
npx skills add https://github.com/nishide-dev/claude-code-ml-research --skill tool-marimo
Please help me install this Agent Skill. Skill: tool-marimo Source: https://github.com/nishide-dev/claude-code-ml-research/tree/main/skills/tool-marimo Command: npx skills add https://github.com/nishide-dev/claude-code-ml-research --skill tool-marimo
It solves the reproducibility and collaboration pain of traditional notebook workflows by replacing hidden, order-dependent execution with deterministic reactive execution in pure Python files.
Tell the AI: “Convert my existing notebook into a marimo .py file, add uv/PEP 723 dependencies, and refactor it into reactive cells with a simple UI control for a key parameter.”
High-intent search queries and answers about installing and using this skill.
Reproducible notebooks eliminate hidden state by using reactive execution based on a dependency DAG, ensuring the correct cells re-run automatically and preventing order-dependent execution errors in data science workflows.
Yes, you can convert existing notebooks into pure .py files that store content as plain Python scripts, enabling clean git diffs and reliable code reviews while maintaining interactive notebook functionality.
PEP 723 metadata enables reproducible sandboxed execution by defining dependencies consistently within the notebook file, allowing uv to manage and isolate the execution environment automatically.
AI-assisted coding is optimized by using pure Python notebook files with explicit, machine-readable structure and strict variable scoping, making LLM edits more dependable and preventing hidden state errors.
Yes, reactive notebooks can be deployed as parameterized dashboards, shareable research apps, or WASM serverless HTML exports, allowing interactive data science workflows to be distributed without backend infrastructure.
uv is used to manage dependencies consistently and reproducibly via PEP 723 metadata, ensuring the sandboxed execution environment is strictly controlled and portable across different machines.
RDCrystalLabCreate marimo notebooks as Python files with reactive cells and PEP 723 dependencies.
synapticore-ioBuild interactive, reactive Python notebooks with MCP integration and deployment workflows.
pymc-labsRun Python notebooks with reactive cell execution on dependencies.
Z43LExecute Python code in a live Jupyter kernel with persistent state.
