More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    prepro auto

    1

    Profile, clean, and transform local tabular data with a verifiable phased training workflow.

    Free

    2 usesSecurity scanned
    prepro auto

    prepro auto

    Example session with this skill installed

    Using sample.csv, keep rows where bath is no greater than size plus one. Exclude rows with missing bath values. Show the preview, apply this rule, and export cleaned.csv. Leave all other values unchanged.

    • Read your context and instructions
    • Compiled the prepro auto
    • Generated the data export

    Dataset filtering completed

    This demonstration uses the supplied synthetic sample.csv. Results were verified through the PrePro Auto helper running through Python stdin.

    Rule applied

    df[df['bath'] <= df['size'] + 1]
    

    For size = 2, bath = 3 is retained and bath = 4 is removed. Missing bath values are excluded, as requested.

    Preview and committed result

    MeasureBeforeAfter
    Rows107
    Columns66
    Active dataset version01

    Three rows were removed

    • Original position 3: size 2, bath 4.
    • Original position 5: size 3, bath 5.
    • Original position 7: missing bath.

    Complete exported dataset

    idsizebathtotal_sqftlocationprice
    1221056Whitefield39
    2231200Whitefield51
    4341600Indiranagar95
    611600Electronic City25
    8221000Missing40
    9452200Whitefield150
    10321500Electronic City75

    Export produced: cleaned.csv.

    “Missing” above represents an empty CSV field. The location value for id 8 remains missing because this request only authorized row filtering.

    The operation was committed as one undoable dataset version. The next step is to review remaining missing values before choosing features and planning model training.

    sample.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

    Dirty, unoptimized data is the primary bottleneck for supervised learning. Manually writing scripts for cleaning, scaling, and encoding is repetitive and error-prone. PrePro Auto provides a structured agentic workflow to profile local datasets, apply verifiable cleaning steps, and compare model performance without manual boilerplate.

    What it does

    • Data Profiling returns dataset shape, missingness patterns, and actual-row evidence for inspection.
    • Verifiable Cleaning generates proposed cards for outlier removal, scaling, and imputation before execution.
    • Deterministic Transforms applies exact row/column rules using expression previews to validate logic against boundary cases.
    • Model Comparison runs cross-validation across multiple supervised candidates to identify the champion model.
    • Managed Exports handles dataset revisions and model artifacts in a local workspace with undoable edits.

    How it works

    1. Bootstrap the environment by piping the agent script into Python to initialize the workspace and install dependencies.
    2. Upload a local CSV, Excel, Parquet, or JSON file to create a tracked job and background server instance.
    3. Analyze the dataset using inspect to review cards and recommendations for cleaning or encoding.
    4. Execute approved proposals to commit changes, update the dataset revision, and generate training-ready artifacts.

    Frameworks & tools

    This skill utilizes a self-contained Python helper (3.10+) to interface with the MIT-licensed PrePro Auto package. It manages local datasets in CSV, Excel, Parquet, JSON, and Feather formats.

    Why this beats prompting it yourself

    Generic LLMs often hallucinate data distributions or write cleaning scripts that fail on edge cases. This skill uses a local runtime to provide real-row evidence and stale-check protection, ensuring every transformation is verified against actual data before it is applied.

    Use cases

    • Automating feature engineering and encoding for tabular ML datasets.
    • Comparing XGBoost, Random Forest, and Linear models on a target variable.
    • Identifying and fixing data quality issues in large local CSV or Parquet files.
    • Exporting cleaned, staged data and trained model artifacts for production.

    Known limitations

    Requires a local Python 3.10+ environment with process execution and loopback HTTP. Not compatible with remote connectors that lack local filesystem or background process persistence.

    Human-in-the-Loop Strictly applies, do not blindly trust everything, Requires Python 3.10+, process execution, and background process persistence. Browser-based loopback URL is restricted to the local network namespace. AI recommendations require manual opt-in.

    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

    2 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 24 days ago

    • Free with an Agensi account

    Requires

    GitHub
    Stripe
    Groq
    OpenAI
    Anthropic
    Pypi
    Pythonhosted
    Python 3.10+
    pip
    venv
    Internet access
    Python
    macOS

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables

    Allowed Hosts

    pypi.org
    files.pythonhosted.org
    api.github.com
    api.stripe.com
    api.groq.com
    api.openai.com
    api.anthropic.com

    File Scopes

    prepro-workspace/**
    data/**
    exports/**

    Reads user-selected datasets and writes runtime configuration, a virtual environment, SQLite history, snapshots, logs and requested exports. Network access downloads PrePro Auto and dependencies from pypi.org/files.pythonhosted.org and communicates with the workspace service on 127.0.0.1. Environment variables configure workspace storage, disable PrePro Auto AI at startup and limit default CPU use. Skill helper code and the server bootstrap run through stdin without saving those scripts to disk.

    Listed1 month ago
    Updated24 days ago

    What's inside

    Frequently Asked Questions

    PrePro Auto automates the manual, error-prone tasks of data cleaning, encoding, and feature engineering. It provides a structured workflow that gives you verifiable evidence of data quality and model performance before you commit to a training run.

    This skill requires a local Python 3.10+ environment with the ability to run background processes and access the local filesystem. It is designed for developers who need to process local CSV, Excel, Parquet, or JSON files securely on their own hardware.

    Unlike general-purpose prompts that may hallucinate data distributions, PrePro Auto uses a local runtime to inspect actual rows and patterns. It generates verifiable 'proposals' for cleaning and encoding, ensuring the logic is sound against your real data before execution.

    You receive the agentic script to interface with the PrePro Auto package, a self-contained Python helper, and comprehensive documentation for the phased training workflow. The purchase also includes access to local workspace management tools for tracking dataset revisions and model artifacts.

    Run the provided helper through Python stdin using its `setup` command and an absolute workspace path. It creates a virtual environment, installs PrePro Auto 3.0.0 and its dependencies, and saves the workspace configuration. Then run `start` and `upload` to begin working with your dataset. See the included setup instructions for the agent workflow and the [README](https://github.com/Chilliflex/prepro_auto#readme) for installation options, supported formats, and notebook/UI examples.