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

build-notebook

Skill17 starsChanged yesterdayMITView on GitHub

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

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create, improve, or fix Jupyter notebooks iteratively.

    line 8
  2. Very specific:

    Use haiku for quick validation checks

    line 57
  3. Very specific:

    Use sonnet for enrichment and standard fixes

    line 58
  4. Very specific:

    Use sonnet for complex design and orchestration — opus and inherit are never used on po-* posts, except on a lane authorized by name (point …

    line 59

≈ “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

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

CategoryWeightCriteria
Structure15%Valid JSON, metadata, cells
Syntax15%Valid code, markdown, LaTeX
Execution30%No errors, no timeouts
Pedagogy25%Progression, code/markdown ratio, explanations
Content15%Visualizations, formulas, conclusion

Sub-Agents Used

AgentRoleModel
notebook-designerCreate initial structureinherit
notebook-executorRun the notebooksonnet
notebook-validatorEvaluate qualitysonnet
notebook-enricherAdd pedagogical contentsonnet
notebook-cell-iteratorFix specific cellssonnet
notebook-cleanerClean structuresonnet

Model Selection Strategy

  • Use haiku for quick validation checks
  • Use sonnet for enrichment and standard fixes
  • Use sonnet for complex design and orchestration — opus and inherit are never used on po-* posts, except on a lane authorized by name (point 3: myia-po-2024:CoursIA-3) (mandat user 2026-10-10, cf model-delegation.md point 3)

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.