Customer Reply Assistant

    1

    Drafts calm, accurate replies to customer questions and complaints using only the facts and policy you supply, in English or Dutch.

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Customer Reply Assistant

    Example session with this skill installed

    A customer says their parcel arrived damaged and wants a full refund. Our policy: damaged items can be replaced or refunded after a photo is received. Please draft a reply in English.

    • Read your context and instructions
    • Compiled the customer reply assistant

    ## Draft reply Hello, Thank you for letting us know, and I'm sorry your parcel arrived damaged. To look into this, could you send us a photo of the damaged item and its packaging? Once we have it, we can go through the options our policy offers for damaged items, which include a replacement or a refund. Kind regards, [Your name] ## Internal note - Missing: order number, photo of damage, whether the customer prefers a refund or replacement - Not confirmed: the order status and the refund amount - Proposed action (not yet agreed): approve a refund or replacement after the photo is checked **Next steps** - Send the reply, then share the photo and order details so I can adjust the follow-up

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

    About this skill

    Customer Reply Assistant helps you draft replies to customer questions and complaints from the facts and policy you provide, in English or Dutch. It works with Claude and ChatGPT. **What it does** - Identifies what the customer is asking and what can actually be answered - Acknowledges the experience without inventing admissions or blame - Applies only the policy you supply, without making up exceptions, refunds, fees or dates - Produces a ready-to-review reply plus a short internal note listing missing information - Can write a holding reply when key facts are not available yet **Good to know** - It does not send replies, check orders or decide refunds. - It keeps the reply calm even when the customer message is hostile. - Review every reply before sending.

    Limited to English and Dutch. No autonomous actions like sending emails or processing refunds. Cannot access external links or files without host tool support.

    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

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    Permissions

    No special permissions declared or detected

    Listed5 days ago

    What's inside

    Frequently Asked Questions

    This skill acts as a disciplined drafting assistant that prevents AI 'hallucinations' by strictly limiting responses to provided order data and policies, ensuring agents never accidentally promise unauthorized refunds or unverified shipping dates.

    It is framework-agnostic and compatible with any major LLM interface (such as ChatGPT, Claude, or Gemini) where you can paste text and interact with an AI agent.

    The skill specializes in English and Dutch, allowing you to accurately draft or translate professional support responses between these two languages while maintaining a neutral, non-confrontational tone.

    No technical installation is required; upon purchase, you receive the specific logic and configuration instructions needed to deploy the skill within your chosen AI chat environment immediately.

    You will receive the core skill configuration, a guide on how to provide 'facts vs. allegations' for best results, and any future logic updates released to improve drafting accuracy.

    This skill is a drafting tool and does not have direct access to your private data; it only processes the specific order logs and policy snippets you choose to paste into the interface for a given reply.

    New in Writing & Content