Shopify Admin Gift Message Extraction logo

Shopify Admin Gift Message Extraction

Organization
40RTY-ai
shopify-admin-gift-message-extraction

Read-only: extracts gift messages, gift recipients, and gift flags from order custom attributes and notes for fulfillment teams to print on packing slips.

Overview

Publisher40RTY-ai
Repositoryshopify-admin-skills
Skill nameshopify-admin-gift-message-extraction
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 Gift Message Extraction 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/conversion-optimization/shopify-admin-gift-message-extraction
  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/conversion-optimization/shopify-admin-gift-message-extraction .claude/skills/shopify-admin-gift-message-extraction
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Shopify Admin Gift Message Extraction 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 Gift Message Extraction 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 Gift Message Extraction 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

Pulls gift messages, gift-recipient names, and "is_gift" flags from order custom attributes and order notes for orders that are pending or in-progress fulfillment. Produces a single sheet that the fulfillment team can use to print gift cards / inserts and route gift orders correctly. Read-only — no mutations.

Prerequisites

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

Parameters

ParameterTypeRequiredDefaultDescription
storestringyes—Store domain (e.g., mystore.myshopify.com)
days_backintegerno7Lookback window of orders to scan
statusstringnounfulfilledOrder status filter: unfulfilled, partial, any
message_keysarrayno["gift_message","gift_note","Gift Message","Gift Note","message","note_to_recipient"]Custom attribute keys (any case) that may contain a gift message
recipient_keysarrayno["gift_recipient","recipient_name","Gift Recipient","To"]Custom attribute keys that may contain a recipient name
flag_keysarrayno["is_gift","gift","Gift Wrap","gift_wrap"]Custom attribute keys whose presence/value marks an order as a gift
include_order_noteboolnotrueAlso scan the order-level note field for free-text gift messages
formatstringnohumanOutput format: human or json

Safety

ℹ️ Read-only skill — no mutations are executed. Output may contain personal text written by customers — handle the resulting CSV with the same care as any customer data export.

Detection Rules

For each order:

  1. Custom attributes — for each lineItem.customAttributes and order.customAttributes:
    • If key (case-insensitive) ∈ message_keys → capture as gift_message
    • If key ∈ recipient_keys → capture as gift_recipient
    • If key ∈ flag_keys AND value is truthy (true, yes, 1, non-empty string) → set is_gift: true
  2. Order note — if include_order_note: true and order.note matches /gift|recipient|deliver to|message:/i, capture the note as a note_hint
  3. An order qualifies for the report if is_gift: true OR gift_message was captured OR gift_recipient was captured

Workflow Steps

  1. Compute filter: created_at:>='<NOW - days_back days>' and translate status → fulfillment_status:unfulfilled / :partial / no filter

  2. OPERATION: orders — query Inputs: query: <filter>, first: 250, select name, note, customAttributes { key, value }, lineItems { name, quantity, customAttributes { key, value } }, shippingAddress, customer { displayName, defaultEmailAddress { emailAddress } }, pagination cursor Expected output: Candidate orders

  3. Apply detection rules to each order

  4. Build report rows — one per qualifying order, including line items so packers know what to wrap

GraphQL Operations

graphql
# orders:query — validated against api_version 2025-01
query OrdersForGiftExtraction($query: String!, $after: String) {
  orders(first: 250, after: $after, query: $query) {
    edges {
      node {
        id
        name
        createdAt
        note
        displayFulfillmentStatus
        customAttributes {
          key
          value
        }
        shippingAddress {
          firstName
          lastName
          address1
          address2
          city
          provinceCode
          countryCodeV2
          zip
          phone
        }
        customer {
          id
          displayName
          defaultEmailAddress {
            emailAddress
          }
        }
        lineItems(first: 50) {
          edges {
            node {
              id
              name
              quantity
              sku
              customAttributes {
                key
                value
              }
            }
          }
        }
      }
    }
    pageInfo {
      hasNextPage
      endCursor
    }
  }
}

Session Tracking

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

On start, emit:

╔══════════════════════════════════════════════╗
║  SKILL: Gift Message Extraction              ║
║  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>

On completion, emit:

For format: human (default):

══════════════════════════════════════════════
GIFT MESSAGE EXTRACTION  (<days_back> days, status: <status>)
  Orders scanned:        <n>
  Gift orders:           <n>
   ↳ With message:       <n>
   ↳ With recipient:     <n>
   ↳ Flag only:          <n>
  Found in order note:   <n>

  Output: gift_messages_<date>.csv
══════════════════════════════════════════════

For format: json, emit:

json
{
  "skill": "gift-message-extraction",
  "store": "<domain>",
  "period_days": 7,
  "orders_scanned": 0,
  "gift_orders": 0,
  "with_message": 0,
  "with_recipient": 0,
  "flag_only": 0,
  "from_order_note": 0,
  "output_file": "gift_messages_<date>.csv"
}

Output Format

CSV file gift_messages_<YYYY-MM-DD>.csv with columns: order_name, created_at, is_gift, gift_recipient, gift_message, note_hint, ship_to_name, ship_to_address, line_items_summary, customer_email

line_items_summary is a qty × title list joined with ; .

Error Handling

ErrorCauseRecovery
THROTTLEDAPI rate limit exceededWait 2 seconds, retry up to 3 times
Custom attribute key naming inconsistent across themesDifferent storefront templates write different keysCaller can extend message_keys / recipient_keys / flag_keys
Encoded HTML in messagesStorefront stored HTML entitiesDecode &amp;, &#39;, &quot; before printing
Multi-line messagesCustomer pressed Enter inside the inputCSV cells can contain newlines — quote properly when exporting

Best Practices

  • Run twice a day on the morning and afternoon pick wave — gift messages are time-sensitive and missing one ruins the experience.
  • Check custom-attribute key naming against your theme's gift-message implementation; extend message_keys / recipient_keys if your theme uses non-default keys.
  • For peak gifting seasons (Mother's Day, Valentine's, December), expand days_back to 14 and switch status: any to capture orders already in fulfillment.
  • Treat the CSV as PII — gift messages can contain personal sentiments. Restrict access to fulfillment staff who need it.
  • Sort the output by ship_to_address so packers can pull all gift orders going to the same address together.

Frequently asked questions

What does the Shopify Admin Gift Message Extraction AI skill do?

Read-only: extracts gift messages, gift recipients, and gift flags from order custom attributes and notes for fulfillment teams to print on packing slips.

Why use Shopify Admin Gift Message Extraction on TypingMind?

Because you install it once and use it with any model. Shopify Admin Gift Message Extraction 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 Gift Message Extraction in TypingMind?

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

Which AI models can use Shopify Admin Gift Message Extraction?

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 Gift Message Extraction?

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

Is the Shopify Admin Gift Message Extraction 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 👇