notebook-patterns
Skill17 starsChanged yesterdayMITView on GitHub
Pedagogical patterns for enriching notebooks (GameTheory model). Use when adding interpretations, structuring notebooks, or creating educational content in Jupyter notebooks.
- Reads credentials
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
- execute-notebookSkill
- genai-iterateSkill
- mcp-jupyterSkill
- notebook-helpersSkill
- 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
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 56
Use cell_id (not index) for NotebookEdit insert reference
- Distinctive: line 57
Verify position immediately after each insertion
≈ “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
Notebook Enrichment Patterns
Standard Header (all notebooks)
# Series-N-Title
**Navigation** : [Index](README.md) | [<< Precedent](Series-N-1.ipynb) | [Suivant >>](Series-N+1.ipynb)
## Objectifs d'apprentissage
A la fin de ce notebook, vous saurez :
1. ...
2. ...
### Prerequis
- Python 3.10+ / .NET 9.0
- Cle API configuree (.env)
### Duree estimee : XX minutesInterpretation Pattern (after significant code output)
### Interpretation : [Concept Name]
**Sortie obtenue** : [Brief summary of output]
| Aspect | Valeur | Signification |
|--------|--------|---------------|
| ... | ... | ... |
**Points cles** :
1. ...
2. ...
> **Note technique** : [Detail if relevant]Positioning Rules (CRITICAL)
- Introduction cells go BEFORE the code they introduce (future tense)
- Interpretation cells go AFTER the code output they analyze (past tense)
- Transition cells go BETWEEN sections
- Conclusion cells go at the END of a section or notebook
Cell Insertion Strategy
- Work from BOTTOM to TOP to avoid index shifting
- Use
cell_id(not index) for NotebookEdit insert reference - Verify position immediately after each insertion
- One cell at a time - never batch inserts
Domain-Specific Vocabulary
| Domain | Key Terms |
| ML | accuracy, loss, epoch, overfitting, cross-validation |
| Probas/Infer | prior, posterior, distribution, inference, factor graph |
| GameTheory | Nash equilibrium, Shapley value, dominant strategy |
| SymbolicAI | satisfiability, resolution, proof, axiom, theorem |
| GenAI | prompt, tokens, embedding, fine-tuning, hallucination |
| Optimization | fitness, generation, mutation, crossover, convergence |
Code/Markdown Ratios
| Level | Code | Markdown | Visualizations |
| Intro | 35-40% | 55-60% | min 3 |
| Intermediate | 45-50% | 45-50% | min 4 |
| Advanced | 55-60% | 35-40% | min 2 |
Quality Checklist
- Navigation header present
- Learning objectives stated
- No consecutive code cells without explanation
- Every significant output has interpretation
- Summary table at end of each major section
- Conclusion with takeaways
- Progressive difficulty (simple to complex)
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.

