Skip to content
Back to skills

Build Notebook

ASecurity

Build or improve Jupyter notebooks iteratively with quality scoring. Arguments: <new|improve|fix> <path> [--topic] [--domain] [--level] [--quality] [--max-iter]

  • 16 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 20, 2026
educationgo

Security analysis

A100/100

Scanned September 20, 2026

npx -y skills add jsboige/CoursIA --skill build-notebook --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Build Notebook?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Build Notebook
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jsboige-build-notebook/badge)](https://www.skillsdirectory.com/skills/jsboige-build-notebook)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: build-notebook
description: Build or improve Jupyter notebooks iteratively with quality scoring. Arguments: <new|improve|fix> <path> [--topic] [--domain] [--level] [--quality] [--max-iter]
---

# Build Notebook

Create, improve, or fix Jupyter notebooks iteratively.

**Action**: `$ARGUMENTS`

## Actions

### `new` - Create from scratch
Requires: `--topic`, `--domain` (ML, Probas, GenAI, GameTheory, SymbolicAI, Sudoku, Search), `--level` (intro, intermediate, advanced)

### `improve` - Enhance existing notebook
Requires: notebook path, optional `--quality` (0-100, default 90), `--focus` (execution, pedagogy, content, structure)

### `fix` - Correct execution errors
Requires: notebook path, optional `--max-iter` (default 5)

## Iterative Workflow

```
while iteration < max_iterations and score < quality_target:
    1. Execute notebook (notebook-executor agent)
    2. Validate all aspects (notebook-validator agent)
    3. Plan corrective actions (prioritized by severity)
    4. Apply via appropriate sub-agent (enricher, cell-iterator, cleaner)
    5. Re-validate and measure improvement
```

## Quality Scoring

| Category | Weight | Criteria |
|----------|--------|----------|
| Structure | 15% | Valid JSON, metadata, cells |
| Syntax | 15% | Valid code, markdown, LaTeX |
| Execution | 30% | No errors, no timeouts |
| Pedagogy | 25% | Progression, code/markdown ratio, explanations |
| Content | 15% | Visualizations, formulas, conclusion |

## Sub-Agents Used

| Agent | Role | Model |
|-------|------|-------|
| notebook-designer | Create initial structure | inherit |
| notebook-executor | Run the notebook | sonnet |
| notebook-validator | Evaluate quality | sonnet |
| notebook-enricher | Add pedagogical content | sonnet |
| notebook-cell-iterator | Fix specific cells | sonnet |
| notebook-cleaner | Clean structure | sonnet |

## Model Selection Strategy

- Use `haiku` for quick validation checks
- Use `sonnet` for enrichment and standard fixes
- Use `inherit` (or `opus` if available) for complex design and orchestration

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…