Use customer support ticket triage to turn a busy Shopify inbox into a clear work queue. Give this Skill customer messages, confirmed order details and store policies; it drafts priorities, reply text and escalation notes so your team can see what to handle first and what information is still missing.
Shopify Support Triage works on the support material you provide. It separates the customer's request, the facts already known and the next action, then uses a four-level priority rubric to organize the queue. A delayed parcel, a damaged item and a product question can therefore receive different handling instructions.
The output is a working brief for the support team: a proposed reply, missing facts and a named escalation role. Your helpdesk remains responsible for assigning tickets and sending messages.
Urgency and action are assessed separately. A message can be important without having enough evidence for an immediate refund. The handoff keeps the customer's request, available order facts and the decision required from a supervisor together.
Use it at the start of a shift, during a delivery-delay spike or when preparing a supervisor handoff. Supplying your actual policies and responsibilities gives the team replies and next steps that refer to the same operating rules.
Redacted customer messages, confirmed order facts, store policies, and team responsibilities.
A model chat is enough to draft from these instructions. Real system access or file changes need separately configured tools.
The collected text includes no Shopify connector or ticket-routing service. Order facts and response times must be supplied; compensation needs approval.
Use these instructions in a chat, or ask Codex / Claude Code to save them as a personal Skill for repeated tasks.
Set up a personal reusable instruction template for Shopify Support Triage Agent in the app I am using.
1. Read the “Collected instruction template” section at https://ecomagenttools.com/skills/shopify-support-triage. Use only that complete instruction text, not the page’s reviews, FAQ or installation explanation. If you cannot retrieve the complete text, ask me to paste it; do not guess it or download a same-named third-party package.
2. Show which assumptions, placeholders and access requirements I need to supply. Preserve the collected task instructions. This is a locally adapted template, not an original-author package.
3. If you are Codex or Claude Code with local file access, create a personal Skill named shopify-support-triage-local under ~/.agents/skills/shopify-support-triage-local/SKILL.md for Codex or ~/.claude/skills/shopify-support-triage-local/SKILL.md for Claude Code. Add valid name and description frontmatter if absent; keep the collected instructions in the body and identify the local adaptation. Do not overwrite an existing Skill. If you are in a chat-only app, use these instructions in the current conversation instead and do not claim a local installation.
4. Return the saved path or current-chat setup result and a starter request for this task. List any required tools or data that remain unconfigured. Do not claim account/API access or a completed business workflow just because the template was saved.Network-collected; no confirmed author source. The collected text was reviewed, but it has not been linked to a verified original publication. This does not establish that no official package exists; the examples here use only the collected text.
You are a Shopify customer support triage agent for an ecommerce store. Your role:
1. Analyze each incoming customer message and classify it:
- 🚨 URGENT: Refund requests, chargebacks, legal threats
- ⚡ HIGH: Shipping delays, damaged items, wrong orders
- 📋 NORMAL: Product questions, sizing help, stock availability
- 💡 LOW: General feedback, feature requests, thank-you notes
2. For each ticket, draft a response with:
- Empathetic acknowledgment of the issue
- Specific next steps based on category
- Estimated resolution timeline
- One personalized detail from their order history
3. Suggest which team member should handle it based on:
- Order value (high-value → senior agent)
- Issue complexity
- Customer history (repeat issues → manager)
Your tone is warm, professional, and solution-oriented. Never make promises about refunds or compensation — defer those to human approval.Starter prompts for the main use cases—copy and use them directly.
Classify each message as urgent, high, normal, or low; explain the reason and missing facts. Use for: Triage a support queue. Prepare: Redacted customer messages, confirmed order facts, store policies, and team responsibilities.
Use the collected instructions above. Task: Classify each message as urgent, high, normal, or low; explain the reason and missing facts.. Inputs: [INPUT]. Constraints: [CONSTRAINTS]. Check missing information first. Produce a reviewable result with evidence, assumptions, and next steps. The collected text includes no Shopify connector or ticket-routing service. Order facts and response times must be supplied; compensation needs approval.[INPUT][CONSTRAINTS]Acknowledge the delay and draft the next steps using confirmed tracking facts, without inventing a delivery date. Use for: Draft a shipping-delay reply. Prepare: Redacted customer messages, confirmed order facts, store policies, and team responsibilities.
Use the collected instructions above. Task: Acknowledge the delay and draft the next steps using confirmed tracking facts, without inventing a delivery date.. Inputs: [INPUT]. Constraints: [CONSTRAINTS]. Check missing information first. Produce a reviewable result with evidence, assumptions, and next steps. The collected text includes no Shopify connector or ticket-routing service. Order facts and response times must be supplied; compensation needs approval.[INPUT][CONSTRAINTS]Recommend an owner using order value, complexity, and repeat issues; list facts a human must confirm. Use for: Prepare an escalation handoff. Prepare: Redacted customer messages, confirmed order facts, store policies, and team responsibilities.
Use the collected instructions above. Task: Recommend an owner using order value, complexity, and repeat issues; list facts a human must confirm.. Inputs: [INPUT]. Constraints: [CONSTRAINTS]. Check missing information first. Produce a reviewable result with evidence, assumptions, and next steps. The collected text includes no Shopify connector or ticket-routing service. Order facts and response times must be supplied; compensation needs approval.[INPUT][CONSTRAINTS]Synthetic HarborMug order A100 was delivered on October 20; the buyer requested a return on November 3 for an unopened $24 item. The business brief supplies a 30-day policy and team responsibilities for triage and a first reply.
Case input files: business-inputs.zip
Use the shopify-support-triage Skill.
Our support queue has a return request for order A100. Decide its priority and owner from the return policy and team responsibilities, explain eligibility, and draft the first customer reply with the information we still need. Give the next internal action and escalation condition.
The attached business materials are:
- inputs/brief.json
- inputs/merchant.json
Deliver a complete result.md report that the operations team can read, plus any finished files needed for this task. Keep supporting calculations and evidence with the deliverables. Write the report in English; use the requested target language for customer-facing copy. The business datasets are fictional examples unless the brief explicitly names a live public website.The primary file produced by this prompt is shown below in its original language.
Priority: URGENT. Owner: Mia, frontline support lead. Ticket SYN-N001 explicitly requests a refund, which the Skill classifies as urgent. The input case label “normal” does not override that rule. This is a routine return involving one $24 item, below the supplied $200 senior-agent threshold, with no prior issues recorded. Alex, the escalation lead and senior agent/manager, is the escalation owner.
All case information is synthetic. This report is a proposed handling decision and an unsent reply; no account action, return authorization, or refund has occurred.
The customer reports that the blue 500 ml stainless-steel insulated cup is unopened. The request was received on November 3, 2026, 14 calendar days after delivery on October 20. Under the supplied test assumption that the 30-day return period starts at delivery, the request is within the window, with 16 days remaining at receipt. The calculated 30-day boundary is November 19; it is not a confirmed customer deadline because the actual policy does not specify its start point or boundary handling.
Provisionally eligible for review, subject to confirming the item is unused and human approval. Unopened is the customer's report, not an inspected condition. The merchant explicitly requires manual refund approval. The materials do not establish a return address, authorization process, return postage responsibility, refund amount, refund processing time, or whether the window applies to requesting or receiving a return. Mia must confirm these before providing return instructions. Outbound dispatch and delivery estimates do not establish a return or refund timeline.
林女士，您好！理解您想为 A100 订单中的蓝色 500ml 不锈钢保温杯办理退货退款，感谢您告知商品尚未拆封。
根据现有记录，订单于10月20日签收，您在11月3日提出申请。按本次审核暂以签收日起算30天的口径，申请仍在期限内；具体退货资格和退款需由商家人工审核确认。
为便于审核，请您补充确认：杯子是否完全未使用，商品及原包装目前是否完好？如有破损或其他情况，也请一并说明。
收到完整资料后，我们预计在1个工作日内进行首次人工审核，并向您说明下一步。该时间是预计审核时间，不代表退款获批或最终处理完成时间。请先保留商品和包装，待我们确认退货地址及寄回要求后再寄出。
感谢您的配合！
Mia should mark the ticket urgent and pending customer information, record the request date and reported unopened condition, and use the draft above to request the missing condition details through the team's approved process. No need to ask the customer again for the order number or delivery date already supplied.
In parallel, Mia should verify the return-clock interpretation, request-versus-receipt cutoff, return instructions, postage responsibility, and designated human refund approver with the merchant. Once the condition details are complete, route the case for its first manual review, targeting one business day as an estimate. Only communicate approved return instructions and refund terms after human review; do not invent a refund amount or promise compensation.
Escalate to Alex if condition evidence conflicts with the unused-return rule, the return-clock ambiguity affects eligibility, the customer disputes the decision, repeat issues emerge, or Mia cannot obtain the necessary approval or instructions within the estimated review window. Route refund authorization to the merchant's designated human approver; Alex can coordinate this, but the supplied roles do not establish that Alex personally has refund authority. Senior handling is not triggered by the current $24 value.
eligibility-calculations.json: date arithmetic, value threshold check, and assumptions.evidence.md: source-to-decision trace and unresolved policy details.The review target and delivery-based return clock are explicitly supplied synthetic operating assumptions, not verified merchant service guarantees. No final eligibility or refund decision can be made from these materials alone. Weekly sales context is marked unused in the input and is unnecessary for this ticket.
Merchant business data is synthetic. Website observations, when present, come from the public URLs listed in the report.
The collected text includes no Shopify connector or ticket-routing service. Order facts and response times must be supplied; compensation needs approval.
Network-collected; no confirmed author source. The collected text was reviewed, but it has not been linked to a verified original publication. This does not establish that no official package exists; the examples here use only the collected text.
Use authorized inputs and keep secrets out of prompts. Review customer-facing claims, calculations, code changes, and any proposed external action before applying them.
Classify support messages, draft replies, and suggest who should handle each case. A four-level priority rubric separates urgency from the next action and escalation owner.
Copy the collected instructions below into a model chat or project instructions. Replace assumed access, default policies, sample numbers, and placeholders with your actual context. Attach a small redacted sample, use a starter prompt, and review the draft before acting.
Triage a support queue; Draft a shipping-delay reply; Prepare an escalation handoff
The collected text includes no Shopify connector or ticket-routing service. Order facts and response times must be supplied; compensation needs approval.
Network-collected; no confirmed author source. The collected text was reviewed, but it has not been linked to a verified original publication. This does not establish that no official package exists; the examples here use only the collected text.
The complete available Skill content is cataloged and reviewed; public web material does not currently name the original author. Attribution does not affect its directory visibility or content-based recommendation eligibility.
Network-collected; no author source is listed. This label describes attribution only, not capability, visibility, or recommendation eligibility.
No reviews yet.