More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    CSV Import Contract Repair

    1

    Repair CSV and spreadsheet import drift across encoding, headers, mappings, types, row identity, validation, retries, partial success, and cleanup.

    $1

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    CSV Import Contract Repair

    CSV Import Contract Repair

    Example session with this skill installed

    Repair our CSV import flow. Preview uses header names but the worker uses indices, leading to column shifts. Add idempotency to the worker and ensure the preview token binds the file hash.

    • Read your context and instructions
    • Compiled the csv import contract

    Analyzed import services and BullMQ workers. Found drift in column mapping logic. Planned safe patch: unified parser profile, added file digest to confirmation token, and implemented row-level idempotency via a results ledger. Added deterministic tests for shifted headers.

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

    About this skill

    The problem

    CSV and spreadsheet imports often suffer from contract drift where preview logic, execution workers, and retry handlers interpret files differently. This leads to silent data corruption, duplicate records, and tenant-scope leaks when encoding, locales, or mapping rules vary across the stack.

    What it does

    • Identifies drift between preview parsers and background execution workers.
    • Detects encoding, delimiter, and byte-order mark (BOM) inconsistencies.
    • Adds version-binding to ensure execution matches the exact file digest and mapping confirmed by the user.
    • Implements idempotent row application to prevent duplicate writes during job retries.
    • Neutralizes dangerous formulas and external links in generated error export files.

    Frameworks & tools

    Works with repository-based import logic including pandas, openpyxl, Prisma, SQLAlchemy, BullMQ, Celery, and standard CSV parsers.

    Why this beats prompting it yourself

    Generic prompts often miss the subtle lifecycle gaps between a web-based preview and a background worker. This skill enforces a strict provenance chain from raw bytes to persisted row outcomes, ensuring local verification remains deterministic without needing production data access.

    Use cases

    • Fixing column-shift risks where headers are mapped differently in preview versus execution.
    • Standardizing locale-sensitive date and decimal parsing across heterogeneous environments.
    • Securing multi-tenant imports where referenced IDs must be resolved within strict ownership boundaries.
    • Hardening batch rollback logic to target only mutations owned by a specific import.

    Known limitations

    Does not access production databases, execute live migrations, or certify the accuracy of historical data already imported into the system.

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

    Requires repository files (routes, parsers, schemas). Does not access live production databases, storage, or real customer files. Does not perform deployments or live migrations.

    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 3 months ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Permissions are limited to the active local workspace and are used to inspect user-supplied or local workspace files; create or modify bounded local fixes, tests, documentation, or review artifacts; run repository-supported local tests, checks, builds, or parsing commands. The skill package does not require bundled credentials, unrestricted external network access, or automatic production changes.

    Listed3 months ago
    Updated9 days ago

    What's inside

    Frequently Asked Questions

    This skill bridges the gap between how a file looks in a user's browser and how a background worker processes it, fixing issues like character encoding errors, shifted columns, and incorrect date formatting that lead to data corruption.

    Yes, it is designed to work with popular libraries like pandas and openpyxl, as well as job queue systems like BullMQ and Celery, ensuring consistent logic across your entire data processing stack.

    The skill implements version-binding and byte-level verification, ensuring that the background worker processes the exact same data and mapping rules that the user confirmed during the preview stage.

    You will receive the core logic definitions for the agent, integration templates for common ORMs and parsers, and a guide for implementing the provenance chain in your existing workflow.

    No, the skill operates on the logic and transformation layer; it verifies the integrity of the incoming data and the application logic without requiring direct access to your production database.

    New in Agents & Orchestration