Shopify Admin Refund And Reorder logo

Shopify Admin Refund And Reorder

Organization
40RTY-ai
shopify-admin-refund-and-reorder

Process a full or partial refund on an order and optionally create a replacement draft order for the customer.

Overview

Publisher40RTY-ai
Repositoryshopify-admin-skills
Skill nameshopify-admin-refund-and-reorder
Stars
200
Forks
22
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by 40RTY-ai on GitHub. Read the source before you install it.

Installation

Install the Shopify Admin Refund And Reorder AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/40RTY-ai/shopify-admin-skills/tree/main/skills/customer-support/shopify-admin-refund-and-reorder
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/40RTY-ai/shopify-admin-skills.git /tmp/shopify-admin-skills
mkdir -p .claude/skills
cp -r /tmp/shopify-admin-skills/skills/customer-support/shopify-admin-refund-and-reorder .claude/skills/shopify-admin-refund-and-reorder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Shopify Admin Refund And Reorder in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Shopify Admin Refund And Reorder on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Shopify Admin Refund And Reorder is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Purpose

Processes refunds and creates replacement orders without navigating the Shopify admin UI. This skill handles both the refund and the optional replacement draft order in a single workflow.

Prerequisites

  • Authenticated Shopify CLI session: shopify auth login --store <domain>
  • API scopes: read_orders, write_orders

Parameters

ParameterTypeRequiredDefaultDescription
storestringyes—Store domain (e.g., mystore.myshopify.com)
formatstringnohumanOutput format: human or json
dry_runboolnofalsePreview operations without executing mutations
order_idstringyes—GID of the order (e.g., gid://shopify/Order/12345)
refund_line_itemsarraynoall refundableArray of {line_item_id, quantity} to refund; if omitted, refunds all refundable quantities
reasonstringnootherRefund reason: customer, fraud, inventory, declined, other
create_replacementboolnofalseIf true, create a draft order with the same line items after refund
notify_customerboolnotrueSend refund notification email to customer

Safety

⚠️ Steps 2 and 3 execute irreversible financial mutations. refundCreate cannot be undone — once a refund is processed, the payment cannot be re-captured. draftOrderCreate creates a new draft order that must be invoiced and paid separately. Run with dry_run: true to verify the refund line items and amounts before committing. Verify refundableQuantity per line item from Step 1 before proceeding.

Workflow Steps

  1. OPERATION: order — query Inputs: id: <order_id> Expected output: Full order with displayFinancialStatus, lineItems (with refundableQuantity), transactions, customer, shippingAddress; verify order is refundable before proceeding

  2. OPERATION: refundCreate — mutation Inputs: input.orderId, input.refundLineItems (from parameter or all refundable), input.notify, input.note: <reason> Expected output: refund.id, refund.totalRefundedSet, userErrors

  3. OPERATION: draftOrderCreate — mutation (only if create_replacement: true) Inputs: input.lineItems (from original order line items), input.customerId, input.shippingAddress, input.note: "Replacement for order <name>" Expected output: draftOrder.id, draftOrder.name, draftOrder.invoiceUrl, userErrors

GraphQL Operations

graphql
# order:query — validated against api_version 2025-01
query OrderForRefund($id: ID!) {
  order(id: $id) {
    id
    name
    displayFinancialStatus
    displayFulfillmentStatus
    totalPriceSet {
      shopMoney { amount currencyCode }
    }
    lineItems(first: 50) {
      edges {
        node {
          id
          title
          quantity
          refundableQuantity
          variant {
            id
            sku
            price
          }
        }
      }
    }
    transactions(first: 10) {
      id
      kind
      status
      amountSet {
        shopMoney { amount currencyCode }
      }
      gateway
    }
    refunds {
      id
      createdAt
      totalRefundedSet {
        shopMoney { amount currencyCode }
      }
    }
    customer {
      id
      defaultEmailAddress {
        emailAddress
      }
      firstName
      lastName
    }
    shippingAddress {
      address1
      city
      province
      country
      zip
    }
  }
}
graphql
# refundCreate:mutation — validated against api_version 2025-01
mutation RefundCreate($input: RefundInput!) {
  refundCreate(input: $input) {
    refund {
      id
      createdAt
      totalRefundedSet {
        shopMoney { amount currencyCode }
      }
    }
    userErrors {
      field
      message
    }
  }
}
graphql
# draftOrderCreate:mutation — validated against api_version 2025-01
mutation DraftOrderCreate($input: DraftOrderInput!) {
  draftOrderCreate(input: $input) {
    draftOrder {
      id
      name
      invoiceUrl
    }
    userErrors {
      field
      message
    }
  }
}

Session Tracking

Claude MUST emit the following output at each stage. This is mandatory.

On start, emit:

╔══════════════════════════════════════════════╗
║  SKILL: refund-and-reorder                   ║
║  Store: <store domain>                       ║
║  Started: <YYYY-MM-DD HH:MM UTC>             ║
╚══════════════════════════════════════════════╝

After each step, emit:

[N/TOTAL] <QUERY|MUTATION>  <OperationName>
          → Params: <brief summary of key inputs>
          → Result: <count or outcome>

If dry_run: true, prefix every mutation step with [DRY RUN] and do not execute it.

On completion, emit:

For format: human (default):

══════════════════════════════════════════════
OUTCOME SUMMARY
  Order:               <name>
  Refund ID:           <id>
  Amount refunded:     <amount> <currency>
  Replacement draft:   <draft order name or "none">
  Errors:              0
  Output:              none
══════════════════════════════════════════════

For format: json, emit:

json
{
  "skill": "refund-and-reorder",
  "store": "<domain>",
  "started_at": "<ISO8601>",
  "completed_at": "<ISO8601>",
  "dry_run": false,
  "steps": [
    { "step": 1, "operation": "OrderForRefund", "type": "query", "params_summary": "order <id>", "result_summary": "<status>", "skipped": false },
    { "step": 2, "operation": "RefundCreate", "type": "mutation", "params_summary": "<n> line items, reason: <reason>", "result_summary": "refund <id>", "skipped": false },
    { "step": 3, "operation": "DraftOrderCreate", "type": "mutation", "params_summary": "<n> line items, customer <id>", "result_summary": "draft <name>", "skipped": false }
  ],
  "outcome": {
    "order_name": "<name>",
    "refund_id": "<id>",
    "amount_refunded": "<amount>",
    "currency": "<currency>",
    "draft_order_name": "<name or null>",
    "draft_order_invoice_url": "<url or null>",
    "errors": 0,
    "output_file": null
  }
}

Output Format

No CSV output. The session completion summary reports the refund ID and amount. If create_replacement: true, the draft order name and invoice URL are included in the output.

Error Handling

ErrorCauseRecovery
refundableQuantity is 0Line item already fully refundedCheck order refund history
userErrors from refundCreateInvalid refund amounts or order not refundableCheck displayFinancialStatus — must not be REFUNDED
userErrors from draftOrderCreateInvalid line items or customerVerify product variants still exist
Order not foundInvalid order GIDUse order-lookup-and-summary skill to find the correct order ID

Best Practices

  1. Always run dry_run: true first — Step 2 is irreversible. Verify refundableQuantity per line item in Step 1 output before committing.
  2. For partial refunds, specify refund_line_items explicitly — omitting it refunds all refundable items, which may not be intended.
  3. The create_replacement draft order is not automatically invoiced or fulfilled — share invoiceUrl with the customer for payment.
  4. Use notify_customer: false for internal corrections where the customer should not be alerted.
  5. Check displayFinancialStatus from Step 1 — if it is REFUNDED, there is nothing left to refund.

Frequently asked questions

What does the Shopify Admin Refund And Reorder AI skill do?

Process a full or partial refund on an order and optionally create a replacement draft order for the customer.

Why use Shopify Admin Refund And Reorder on TypingMind?

Because you install it once and use it with any model. Shopify Admin Refund And Reorder is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Shopify Admin Refund And Reorder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/40RTY-ai/shopify-admin-skills/tree/main/skills/customer-support/shopify-admin-refund-and-reorder. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Shopify Admin Refund And Reorder?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Shopify Admin Refund And Reorder?

As many as you like. As long as a model supports skills, you can use Shopify Admin Refund And Reorder with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Shopify Admin Refund And Reorder AI skill free?

Yes. It is published on GitHub by 40RTY-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇