teaching notebook converter

    1

    Converts research and engineering Jupyter notebooks into polished teaching tools with visuals and structured narratives.

    $1

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    teaching notebook converter

    Example session with this skill installed

    Convert the attached resnet_training.ipynb into a standard teaching notebook. Focus on explaining the model architecture and the data augmentation pipeline using 4 visuals.

    • Read your context and instructions
    • Compiled the teaching notebook converter
    • Generated the document

    I have inspected resnet_training.ipynb and initiated a

    standard conversion mode. I have generated a research manifest justifying the use of the Paddle framework and mapped the training stages to a teaching narrative.

    Teaching Conversion: resnet_training.teaching.ipynb

    ArtifactPathDescription
    Teaching Notebookresnet_training.teaching.ipynbThe enriched notebook with 4 teaching visuals and HTML cards.
    Manifestartifacts/teaching_manifest.jsonMapping of source SHA-256 to the new teaching copy.
    Visual Assetsartifacts/teaching_assets/Contains arch_diagram.png, aug_pipeline.png, loss_convergence.png, and eval_metrics.png.
    Prompt Packartifacts/teaching_imagegen_prompts.jsonThe exact prompts and prose-replacement contracts used for visuals.
    Validation Reportartifacts/teaching_validation.json12 passed checks, 0 critical errors.
    
# Example of the enriched teaching cell structure (Conceptual)
# [Cell 1: Markdown] ## 1. Data Augmentation Strategy
# Includes an inline HTML card for parameter summaries.
# [Cell 2: Attachment] ![Data Augmentation Flow](attachment:aug_pipeline.png)
# [Cell 3: Code] 
def get_transforms():
    # Source-locked code preserved for execution
    return Compose([RandomHorizontalFlip(), Normalize()])

    Next steps

    1. Review the artifacts/teaching_research_sources.json to verify the technology selection citations.
    2. Run jupyter nbconvert --to html resnet_training.teaching.ipynb to preview the learner-facing output.
    3. Inspect the aug_pipeline.png in the assets folder to ensure the text-bearing bitmap meets your density requirements.

    arch_diagram.png

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Jupyter notebooks designed for engineering or research often fail as teaching tools because they lack narrative flow, visual hierarchy, and clear technology rationales. This skill converts functional .ipynb files into polished, instructional copies without breaking the underlying code execution path.

    What it does

    • Preserves execution paths by maintaining source code, cell IDs, and metadata while wrapping them in a teaching-oriented narrative.
    • Generates instructional visuals using image generation tools to create process diagrams, system hierarchies, and dependency maps with embedded text.
    • Conducts technology research by documenting why specific frameworks (like Paddle) or libraries were chosen, including tradeoffs and alternatives.
    • Enriches notebooks with inline HTML cards, status gates, metric grids, and learner-focused orientation.
    • Automates validation to ensure all image references resolve, JSON structures remain intact, and the teaching manifest matches the source.

    How it works

    1. Inspection: Runs a diagnostic script on the source notebook to map code stages, magics, and risk signals.
    2. Research: Gathers official documentation and technical evidence to justify library and framework selections.
    3. Planning: Selects a conversion mode (quick, standard, or full) and identifies which sections become visuals vs. Markdown.
    4. Generation: Produces a prompt pack and executes image generation for high-density teaching visuals.
    5. Synthesis: Assembles the teaching copy, compresses redundant prose, and runs a final validation report.

    Frameworks & tools

    This skill works with standard Jupyter Notebook (.ipynb) environments, Python-based notebook APIs, nbconvert, nbclient, and specific engineering ecosystems like Paddle.

    Why this beats prompting it yourself

    Writing prompts to restructure a notebook often results in broken JSON or lost cell metadata. This skill uses structured manifest tracking and validation scripts to ensure the teaching copy remains a functional, runnable engineering asset rather than just a static document.

    Use cases

    • Converting research prototypes into internal engineering onboarding guides.
    • Preparing technical workshop materials from production-grade notebooks.
    • Documenting complex Paddle engineering workflows for external stakeholders.
    • Creating "showcase" notebooks for open-source project documentation.

    Known limitations

    Does not perform raw notebook text editing; requires JSON-based interaction. Cannot execute untrusted notebooks without explicit approval. Visual generation is focused on teaching value, not UI design.

    How to use

    Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scanned

    Verified clean today

    • Passed all security checks, Safe to install

    Requires

    Git

    Listedtoday

    What's inside

    Frequently Asked Questions