CSV Schema Validator: Infer Rules, Check New Files

    1

    Infer a schema from a good CSV and check new files for missing columns, bad types, blanks, duplicates and out-of-range values.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    CSV Schema Validator: Infer Rules, Check New Files

    Example session with this skill installed

    infer examples/good.csv --out schema.json, then validate examples/new.csv --schema schema.json

    • Read your context and instructions
    • Compiled the csv schema validator
    • Generated the data export

    FAIL: examples/new.csv (6 rows) - 5 problem(s)
    row 5, order_id: duplicate of row 2: '1001'
    row 6, date: not a YYYY-MM-DD date: '2026-13-01'
    row 7, customer_email: empty but required
    row 4, region: 'Nort' not in allowed values ['East', 'North', 'South', 'West']
    row 3, amount: not a number: '12,50'

    new.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

    Point it at a CSV you trust and it writes an editable JSON schema: column types (integer, number, date, yes/no, email, text), required columns, unique IDs, min/max, allowed values. Then validate each new export and get every problem with row and column: missing or extra columns, bad numbers or dates, blanks, duplicate IDs, unknown categories. Exit code 1 on failure for scripts and CI, plus a CSV problem report. Offline Python stdlib.

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

    Dates must be YYYY-MM-DD. Numbers with thousands separators or currency signs count as text. Ranges and allowed values come from the sample, so a small sample gives strict rules; use --types-only or edit the schema. Allowed values are only inferred with 20+ rows and up to 10 distinct values. No cross-column rules.

    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 22 days ago

    • Free with an Agensi account

    Software
    Python 3.8+

    Permissions

    File Scopes

    reads
    the
    CSV
    and
    schema
    you
    pass;
    writes
    only
    --out
    --report
    paths

    Network: none. Runs offline.

    Listed22 days ago

    What's inside

    Frequently Asked Questions

    Yes, the schema is plain JSON; delete or change any rule.

    Use --types-only or remove min/max from the schema.

    No, it reports problems only.

    New in Productivity

    Free