More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Machine Learning Essentials

    1

    Train, validate and communicate tabular ML models in Python and R. 10 ordered skills, starting with Machine Learning, Data Science, Predictive Modeling.

    Free

    Security scanned
    Machine Learning Essentials

    Machine Learning Essentials

    Example session with this skill installed

    A fictional subscription company, "Northwind Streams", wants to predict which customers will cancel in the next 30 days so the retention team can call the highest-risk 500 per week. Dataset (fictional): 48,000 customer-month rows, 6% cancel.

    • Read your context and instructions
    • Compiled the machine learning essentials

    Model report: Northwind retention

    Question / decision: weekly list of 500 customers most likely to cancel within 30 days
    Task type and target: binary classification, cancelled_within_30d (prevalence 6%)
    Data: 48,000 rows; dropped cancellation_reason_code (post-outcome leakage), removed 3% duplicates
    Split strategy and seeds: grouped by customer, last 2 months held out, seed 7
    Baselines: dummy accuracy 0.94 but recall 0; logistic average precision 0.21
    Candidates: logistic 0.21 | forest 0.25 +/- 0.03 | gradient boosting 0.27 +/- 0.02
    Chosen model: histogram gradient boosting with early stopping
    Held-out test result: precision@500 0.19, recall@500 0.31
    Known weaknesses: weak on customers with under 2 months tenure
    Reproducibility: versions and seeds recorded
    Recommendation: pilot the list for 4 weeks, track realized cancels versus a random-call control group, retrain monthly.

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

    About this skill

    The problem

    Beginner data scientists often need a repeatable process, not a one-off prompt. This pack targets: Train, validate and communicate tabular ML models in Python and R.

    What's inside (10 skills, suggested learning order)

    1. Machine Learning — Build predictive models.
    2. Data Science — Apply statistics and ML to business problems.
    3. Predictive Modeling — Predict outcomes from historical data.
    4. Supervised Classification — Classify categories with models.
    5. Regression Analysis — Model numerical relationships.
    6. Unsupervised Learning — Clustering and dimensionality reduction.
    7. Tabular ML with Gradient Boosting — High-performance tree models.
    8. Model Selection and Validation — Cross-validation and metrics.
    9. Jupyter and Reproducible Notebooks — Document executable analyses.
    10. R for Statistics — Statistical analysis in R.

    Why a skill pack instead of a one-off prompt

    Each skill gives the agent a defined trigger, step-by-step procedure and output format, so results are consistent across sessions and easier to review.

    How to use

    1. Install the pack in your SKILL.md-compatible agent.
    2. Ask for the task in plain language (for example: "build predictive models").
    3. Review the output against the skill's quality checks before using it.

    Outputs are drafts that need human review; they are not professional, legal or financial advice. Tools, APIs and prices change; check current vendor documentation before relying on version-specific details. Quality depends on the context you give the agent (data, requirements, constraints). Instruction-only skills: they produce documents and plans, not running software.

    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 any payment.

    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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 8 days ago

    • Free with an Agensi account

    Requires

    Python

    Permissions

    No special permissions declared or detected

    Listed8 days ago

    What's inside

    Frequently Asked Questions

    10 skills, each with SKILL.md and references/sources.md: Machine Learning; Data Science; Predictive Modeling; Supervised Classification; Regression Analysis; Unsupervised Learning; Tabular ML with Gradient Boosting; Model Selection and Validation; Jupyter and Reproducible Notebooks; R for Statistics.

    Beginner data scientists.

    Agents that read the SKILL.md format. See the Compatibility note for what was actually tested.

    New in Data & Databases