execute-notebook
Skill17 starsChanged yesterdayMITView on GitHub
Execute Jupyter notebooks using local scripts or MCP Jupyter. Arguments: <notebook_path> [--mode] [--cells] [--timeout] [--batch] [--save]
- Reads credentials
- Installs packages
In this repository19 other files it gives its agents.
- .vibe/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- adjoint-secretarySkill
- analyze-slidesSkill
- build-notebookSkill
- check-cell-orderSkill
- cleanup-notebooksSkill
- coordinate-adjointSkill
- coordinateSkill
- enrich-notebooksSkill
- genai-iterateSkill
- mcp-jupyterSkill
- notebook-helpersSkill
- notebook-patternsSkill
- qc-iterative-improveSkill
- review-student-prsSkill
- train-modelSkill
- validate-genaiSkill
- verify-notebooksSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 46
Check .env configuration first (use /validate-genai)
- Very specific: line 47
Use --batch for notebooks with interactive widgets
- Very specific: line 48
Use dedicated scripts: python scripts/genai-stack/validate_notebooks.py
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Execute Notebook
Execute a Jupyter notebook with full lifecycle management.
Notebook: $ARGUMENTS
Options
--mode: full (default), selective, papermill--cells: Specific cells (e.g., 0,5,10)--timeout: Per-cell timeout in seconds (default 300)--stop-on-error: Halt on first error--batch: Enable BATCH_MODE for interactive notebooks--save: Save outputs to original notebook
Execution by Kernel Type
Python (kernel: python3)
Local scripts (preferred for batch):
# Full execution via notebook_tools.py
python scripts/notebook_tools/notebook_tools.py execute {path} --timeout 300
# Cell-by-cell with verbose output via notebook_helpers.py
python scripts/notebook_tools/notebook_helpers.py execute {path} --verbose
# Specific cell execution
python scripts/notebook_tools/notebook_helpers.py execute {path} --cell 5 --timeout 60MCP (for interactive debugging):
manage_kernel(action="start", kernel_name="python3")+execute_on_kernel
.NET (kernel: .net-csharp)
- MCP cell-by-cell ONLY - Papermill and local scripts do NOT work with .NET kernels
- CRITICAL: Set working directory first with
SetCurrentDirectory() - See
mcp-jupyterskill for detailed .NET patterns
GenAI notebooks
- Check
.envconfiguration first (use/validate-genai) - Use
--batchfor notebooks with interactive widgets - Use dedicated scripts:
python scripts/genai-stack/validate_notebooks.py
Error Handling
| Error | Cause | Solution |
| Kernel timeout | .NET cold start | Retry (30-60s normal) |
| File not found | Wrong directory | SetCurrentDirectory() |
| ModuleNotFoundError | Missing dependency | pip install |
| API key missing | .env not configured | Check OPENAI_API_KEY etc. |
Report Format
Report: notebook name, kernel, mode, total/executed/successful/error cells, timing, error details.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

