ML Spec Author: Safe JSON ML Specs from Plain English

    1

    Turns a plain-English ML request into a validated, code-free Open MLSpec JSON spec, with data-health checks and a plain-English explanation.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    ML Spec Author: Safe JSON ML Specs from Plain English

    Example session with this skill installed

    I've got our customer export, one row per customer with a churned column. Set up a model that predicts who will churn. Don't train anything yet, I just want a spec our ML platform can run.

    • Read your context and instructions
    • Compiled the ml spec author
    • Generated the data export

    Plan: write churn.mlspec.json, a spec that predicts churned (yes/no) from plan, monthly spend, support tickets and recent logins. This is a classification task with a stratified 80/20 split, comparing logistic regression with a random forest on AUC.

    1. What the data looks like (mlspec.py inspect customers.csv --target churned)

    ColumnTypeRole
    customer_ididentifieridentifier
    signup_datedatetimeignore
    plancategorical (basic, pro, team)feature
    monthly_spendnumeric, min 0feature
    support_ticketsnumeric, min 0feature
    logins_last_30dnumeric, min 0feature
    churnedcategorical (no, yes)target

    500 rows, no nulls, no health warnings. signup_date is set to ignore: a raw date would let the model learn the calendar rather than behaviour. Add a tenure feature later if you want it.

    2. The spec (churn.mlspec.json, written next to your CSV)

    • Dataset: customers.csv, with customer_id unique and churned never null.
    • Split: stratified on churned, 80% train and 20% test, seed 42.

    Models: sklearn.linear_model.LogisticRegression 1.5.2 (class_weight: balanced) and sklearn.ensemble.RandomForestClassifier 1.5.2 (300 trees, balanced).

    • Metrics: auc, pr_auc (useful if churners are rare) and f1.
    • Workflow: fit_logreg and fit_forest, then pick_best by AUC, then why to explain the forest.

    3. Validation

    The first draft gave signup_date the role metadata, and the validator refused it:

    "valid": false
    datasets.customers.schema.columns.1.role: 'metadata' is not one of ['feature', 'target', 'identifier', 'timestamp', 'group', 'weight', 'ignore', ...]
    

    After changing the role to ignore:

    { "valid": true, "errors": [], "advisories": [] }
    

    Next steps

    • Nothing has been trained, so there are no accuracy numbers yet. Run the spec on an MLSpec-compatible runtime to get them.
    • If churners are under about 10% of rows, compare models on pr_auc instead of auc.
    • Want a forecast of churn by month instead? Ask, and I'll write a forecasting spec with a time-based split.

    customers.csv

    CSV · data export

    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

    Describe what you want to predict or forecast, and your agent writes a declarative Open MLSpec JSON spec instead of training code: dataset schema, split, features, model, metrics and workflow steps.

    What it does

    • Profiles your CSV first (mlspec.py inspect): proposes column types and roles, the target and the task, and warns about leakage, class imbalance or too few rows. Samples from columns that look like personal data are withheld.
    • Writes the spec using only registered model families, metrics and operations at pinned versions. Nothing is invented.
    • Validates it (mlspec.py validate) against the bundled JSON schema, a safety scan, the plugin registry and the workflow rules. Refusals go back to the agent, which fixes them. A spec is never called valid unless the script said so.
    • Explains it in plain English: what will be predicted, how the data is split, which models are compared and why.

    Covers classification, regression, time-series forecasting and exploratory charts. Four example specs are included.

    Why it is safe

    • Declarative only: no Python, shell or SQL is written or run to train anything, and no code goes into a spec.
    • No accuracy numbers are ever claimed, because nothing is trained.
    • Your data stays local, and database credentials are referenced by environment-variable name, never read or printed.
    • Python 3.10+ standard library only. No network access.

    To train, run the validated spec on an MLSpec-compatible runtime.

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

    Writes and validates specs only; it does not train, score or forecast, and it never reports accuracy. Covers classification, regression, forecasting and exploratory charts, not clustering or custom losses. CSV inspection loads the whole file into memory. Requires Python 3.10+.

    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

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 9 days ago

    • Free with an Agensi account

    Software
    Python 3.10+

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Runs the bundled scripts/mlspec.py locally to profile a CSV the user names and to validate the spec. Reads only files the user points to, writes the spec next to the data after asking, and makes no network requests.

    Listed9 days ago

    What's inside

    Frequently Asked Questions

    This skill provides the validated JSON configuration (the blueprint) for a machine learning task, not the training execution itself. It ensures your ML plan is logically sound and schema-compliant so that your external training runtimes can execute it without errors.

    The skill integrates a local validation tool and a plugin registry to check against official Open MLSpec schemas. Unlike generic models that might hallucinate parameters, this skill iteratively repairs the JSON until it passes a multi-stage validation check for syntax and data science logic.

    Classification, regression, time-series forecasting and exploratory charts. The bundled plugin registry pins every family and version: scikit-learn linear models, random forests and preprocessing, XGBoost, statsmodels Exponential Smoothing and SARIMAX, Prophet, small PyTorch MLPs, text embeddings and classifiers, and simple ensembles and candidate searches. The skill never invents a family that is not in the registry.

    The SKILL.md instructions, scripts/mlspec.py (inspect and validate, Python standard library only), the Open MLSpec JSON schema, a reference guide to every spec field and the plugin registry, and four example specs (churn classification, home-price regression, weekly sales forecast and an exploratory analysis). There is no training runtime: running a spec needs an MLSpec-compatible runtime.

    The inspect step reads a local CSV (or TSV) and loads it into memory. Column names used in a spec must be lowercase snake_case, and inspect lists any that need renaming in a copy of your file. A spec can point at a database through source.connectionRef, the name of an environment variable your runtime reads; the skill never reads or prints that value.

    New in Data & Databases

    Free