agentleFS
jsboigejsboige/CoursIA/.claude/skills/execute-notebook/SKILL.md

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

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
  1. Very specific:

    Check .env configuration first (use /validate-genai)

    line 46
  2. Very specific:

    Use --batch for notebooks with interactive widgets

    line 47
  3. Very specific:

    Use dedicated scripts: python scripts/genai-stack/validate_notebooks.py

    line 48

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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 60

MCP (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-jupyter skill for detailed .NET patterns

GenAI notebooks

  • Check .env configuration first (use /validate-genai)
  • Use --batch for notebooks with interactive widgets
  • Use dedicated scripts: python scripts/genai-stack/validate_notebooks.py

Error Handling

ErrorCauseSolution
Kernel timeout.NET cold startRetry (30-60s normal)
File not foundWrong directorySetCurrentDirectory()
ModuleNotFoundErrorMissing dependencypip install
API key missing.env not configuredCheck OPENAI_API_KEY etc.

Report Format

Report: notebook name, kernel, mode, total/executed/successful/error cells, timing, error details.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.