Shopify Admin Return Initiation logo

Shopify Admin Return Initiation

Organization
40RTY-ai
shopify-admin-return-initiation

Create a formal Shopify Return record for an order, specifying line items, quantities, and return reason — the first step in the native returns workflow.

Overview

Publisher40RTY-ai
Repositoryshopify-admin-skills
Skill nameshopify-admin-return-initiation
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 Return Initiation 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-return-initiation
  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-return-initiation .claude/skills/shopify-admin-return-initiation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Shopify Admin Return Initiation 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 Return Initiation 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 Return Initiation 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

Initiates a formal Shopify Return on a delivered order — specifying which line items to return, quantities, and reason. This creates the return record in Shopify's native returns system (distinct from simply issuing a refund). Used by support agents when a customer contacts them to return delivered items. The return record enables tracking, warehouse inspection, and exchange/refund resolution downstream. Note: returnCreate requires the order to be in FULFILLED status. For orders that haven't shipped yet, use cancel-and-restock instead. For already-returned items needing a refund, use refund-and-reorder.

Prerequisites

  • shopify auth login --store <domain>
  • API scopes: read_orders, write_returns

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)
return_line_itemsarraynoall fulfilledArray of {fulfillment_line_item_id, quantity, reason, reason_note} to return
return_reasonstringnoOTHERDefault return reason for all items if not specified per-item: SIZE_TOO_SMALL, SIZE_TOO_LARGE, WRONG_ITEM, NOT_AS_DESCRIBED, DEFECTIVE, STYLE, COLOR, UNWANTED, OTHER
notify_customerboolnotrueSend return initiation notification email to customer

Safety

⚠️ Step 2 executes returnCreate which creates a formal return record and — if notify_customer: true — sends an email to the customer. This is appropriate only after verifying with the customer that a return is expected. Run with dry_run: true to preview the return line items and quantities before committing.

Workflow Steps

  1. OPERATION: order — query Inputs: id: <order_id> Expected output: Order name, displayFulfillmentStatus (must be FULFILLED — abort if not), fulfillments with fulfillmentLineItems including id, quantity, discountedTotalSet

  2. OPERATION: returnCreate — mutation Inputs: returnInput.orderId, returnInput.returnLineItems array (each with fulfillmentLineItemId, quantity, reason, customerNote) Expected output: return.id, return.status: OPEN, userErrors

GraphQL Operations

graphql
# order:query — validated against api_version 2025-01
query OrderForReturn($id: ID!) {
  order(id: $id) {
    id
    name
    displayFulfillmentStatus
    displayFinancialStatus
    customer {
      id
      defaultEmailAddress {
        emailAddress
      }
      firstName
      lastName
    }
    fulfillments {
      id
      status
      fulfillmentLineItems(first: 50) {
        edges {
          node {
            id
            quantity
            lineItem {
              title
              variant {
                id
                sku
              }
            }
            discountedTotalSet {
              shopMoney { amount currencyCode }
            }
          }
        }
      }
    }
  }
}
graphql
# returnCreate:mutation — validated against api_version 2025-01
mutation ReturnCreate($returnInput: ReturnInput!) {
  returnCreate(returnInput: $returnInput) {
    return {
      id
      status
      order {
        id
        name
      }
    }
    userErrors {
      field
      message
    }
  }
}

Session Tracking

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

On start, emit:

╔══════════════════════════════════════════════╗
║  SKILL: return-initiation                    ║
║  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>
  Return ID:           <id>
  Line items included: <count>
  Return status:       <status>
  Customer notified:   <yes/no>
  Errors:              0
  Output:              none
══════════════════════════════════════════════

For format: json, emit:

json
{
  "skill": "return-initiation",
  "store": "<domain>",
  "started_at": "<ISO8601>",
  "completed_at": "<ISO8601>",
  "dry_run": false,
  "steps": [
    { "step": 1, "operation": "OrderForReturn", "type": "query", "params_summary": "order <id>", "result_summary": "<status>", "skipped": false },
    { "step": 2, "operation": "ReturnCreate", "type": "mutation", "params_summary": "<n> line items, reason: <reason>", "result_summary": "return <id>", "skipped": false }
  ],
  "outcome": {
    "order_name": "<name>",
    "return_id": "<id>",
    "return_status": "<status>",
    "line_items_count": "<count>",
    "customer_notified": "<true/false>",
    "errors": 0,
    "output_file": null
  }
}

Output Format

No CSV output. The session summary reports the return ID and status. Line items included in the return are listed in the step 2 output.

Error Handling

ErrorCauseRecovery
displayFulfillmentStatus not FULFILLEDOrder hasn't shipped yetUse cancel-and-restock for unfulfilled orders
fulfillmentLineItemId not foundLine item ID doesn't belong to this order's fulfillmentsRe-query the order to get correct fulfillment line item IDs
userErrors from returnCreateInvalid quantity or reasonCheck quantity doesn't exceed fulfillmentLineItem.quantity
Return already existsA return was already created for these itemsCheck order returns in Shopify admin

Best Practices

  1. Always run dry_run: true first — confirm the fulfillment line item IDs and quantities before creating the return record.
  2. The return-initiation skill creates the return record only — it does not issue a refund. After inspecting the returned item, use refund-and-reorder to process the monetary refund.
  3. Set reason per line item when items have different return reasons — this improves your returns analytics in Shopify.
  4. For exchanges (not refunds), create the return record here and then use refund-and-reorder with create_replacement: true to generate a replacement draft order.
  5. The return status will be OPEN after creation — it moves to IN_PROGRESS when a return label is generated and CLOSED when the refund is processed.

Frequently asked questions

What does the Shopify Admin Return Initiation AI skill do?

Create a formal Shopify Return record for an order, specifying line items, quantities, and return reason — the first step in the native returns workflow.

Why use Shopify Admin Return Initiation on TypingMind?

Because you install it once and use it with any model. Shopify Admin Return Initiation 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 Return Initiation 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-return-initiation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Shopify Admin Return Initiation?

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 Return Initiation?

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

Is the Shopify Admin Return Initiation 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 👇