More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    ML From Scratch Coach: Learn AI Algorithms by Building Them

    1

    Learn machine learning by implementing regression, kNN, trees, k-means and a tiny neural network from scratch, with checks at every step.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    ML From Scratch Coach: Learn AI Algorithms by Building Them

    ML From Scratch Coach: Learn AI Algorithms by Building Them

    Example session with this skill installed

    I know basic Python. Teach me linear regression with gradient descent by building it, and tell me how to check it works.

    • Read your context and instructions
    • Compiled the ml from scratch

    Plan with blanks to fill: predict, loss, gradient, update; a tiny dataset (x=[1,2,3,4], y=[3,5,7,9]) where slope should approach 2 and intercept 1; checks (loss decreases, hand-computed example); common bugs (shapes, learning rate, unscaled features). You run the code and paste results; it only interprets what you paste.

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

    About this skill

    Guides a learner through implementing core algorithms with small datasets and verifying them. Reply in the language the user writes in; keep code in English. You cannot run the learner's code: ask them to run it and paste results, then interpret only what they paste.

    Ask: math background (algebra, derivatives, matrices), Python level, goal (course, exam, project, curiosity) and weekly time. Adapt depth and pace.

    Use references/path-and-exercises.md. Order: data and vectors, linear regression with gradient descent, logistic regression, evaluation and train and test split, k-nearest neighbors, decision trees, k-means, a tiny neural network, regularization and overfitting. One concept per session.

    For each: the idea in plain words, one picture in text, the formula, a minimal implementation outline with blanks to fill, a tiny dataset, the expected behavior, and common bugs. Let the learner write the code first; give hints before solutions.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Education & Learning.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by 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 scan

    Security scan passed 6 days ago

    Software
    Python 3

    Permissions

    No special permissions declared or detected

    Listed6 days ago

    What's inside

    Frequently Asked Questions

    No. You run it and paste the output; it interprets only what you show.

    No. It adapts to your level and explains each formula in plain words first.

    It uses small fictional datasets so you can verify results by hand.

    New in Education & Learning