agentleFS
jsboigejsboige/CoursIA/.claude/skills/verify-notebooks/SKILL.md

verify-notebooks

Skill17 starsChanged yesterdayMITView on GitHub

Verify and test Jupyter notebooks with iterative fixing. Arguments: [target] [--quick] [--fix] [--python-only] [--dotnet-only]

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 0 are distinctive, and 4 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.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Verify and test Jupyter notebooks in the CoursIA repository.

    line 8
  2. Very specific:

    Discover notebooks: - Use python scripts/notebook_tools/notebook_tools.py validate {target} --quick for rapid discovery and structure check

    line 22
  3. Very specific:

    If --fix: Use notebook-cell-iterator agent (model: sonnet) for targeted cell corrections (max 3 attempts)

    line 29
  4. Very specific:

    Use /validate-genai to validate the stack before running notebooks.

    line 52

≈ “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

Verify Notebooks

Verify and test Jupyter notebooks in the CoursIA repository.

Target: $ARGUMENTS

Arguments

  • target: Notebook path, family name (Sudoku, Search, SymbolicAI, ArgumentAnalysis, GenAI, ML, Probas, IIT, Tweety, Lean, GameTheory), or all
  • --quick: Structure validation only, no execution
  • --fix: Attempt automatic fixes (max 3 attempts per cell)
  • --python-only / --dotnet-only: Filter by kernel type

Process

  1. Parse target - Determine individual file, family, or all
  2. Discover notebooks - Use python scripts/notebook_tools/notebook_tools.py validate {target} --quick for rapid discovery and structure check
  3. Categorize by kernel - python scripts/notebook_tools/notebook_helpers.py detect-kernel {path}
  4. Execute tests:
    • Python (preferred): python scripts/notebook_tools/notebook_tools.py execute {target} --timeout 300
    • Python (alternative): python scripts/notebook_tools/notebook_helpers.py execute {path} --verbose (cell-by-cell with output)
    • .NET: MCP cell-by-cell only (see mcp-jupyter skill) - Papermill does NOT work
  5. Analyze errors - python scripts/notebook_tools/notebook_helpers.py list {path} --verbose to inspect failed cells
  6. If --fix: Use notebook-cell-iterator agent (model: sonnet) for targeted cell corrections (max 3 attempts)
  7. Generate summary report

Family Reference

FamilyPathKernelNotes
SudokuSudoku/MixedC# (#!import, cell-by-cell only) + Python, one twin per notebook
SearchSearch/MixedGeneticSharp=C#, PyGad=Python
SymbolicAISymbolicAI/MixedTweety=Python+JPype
GenAIGenAI/PythonAPI keys required, use /validate-genai first
ProbasProbas/.NET C#Infer.NET
GameTheoryGameTheory/Python (WSL)OpenSpiel
LeanSymbolicAI/Lean/Lean 4 / Python (WSL)WSL kernels

GenAI-Specific

For GenAI notebooks, use dedicated scripts:

python scripts/genai-stack/validate_stack.py
python scripts/genai-stack/validate_notebooks.py MyIA.AI.Notebooks/GenAI/Image/

Use /validate-genai to validate the stack before running notebooks.

Known Limitations

  1. Widgets/interactive notebooks cannot run in batch mode
  2. GenAI notebooks require GPU for some operations
  3. .NET cold start may timeout initially (30-60s), retry once
  4. External services (DBpedia, etc.) may be unavailable

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.