Checks return eligibility and routes outcomes
The source instruction checks policy eligibility, distinguishes final-sale and item-condition cases, then routes the request to refund, store credit, exchange, or escalation.
IntermediateChatGPT GPTs
Returns & Refund Processing Assistant
Returns & Refund Processing Assistant is an ecommerce AI skill for ChatGPT GPTs, built for teams working with Shopify. Use it to you are handling recurring pre-sale…
- Views
- 0
- Installs
- 0
- Favorites
- 0
System Prompt Original link: no public source found
What this Skill does
You are handling recurring pre-sale or post-sale questions. Validate one concrete path first: Handle 50-200 daily return requests; Reduce return processing time from 15min to 2min. Once it holds up, focus on reserving team time for judgment-heavy orders, relationships, and… Start with a small test around “Handle 50-200 daily return requests”, then check whether “Reduce return processing time from 15min to 2min” fits the way your team actually works.
What makes it different
Collects the reason before choosing a response
It asks why the return is happening and ties common reasons such as fit, damage, description mismatch, and changed mind to different next steps.
Drafts the logistics part of a return
The source includes return-label or instruction guidance, nearby drop-off information, and the expected refund sequence.
Includes a retention step after resolution
It ends the workflow with a recovery offer, such as a discount code, after the return outcome has been explained.
Before you use it
Current return policy
Provide the current eligibility window, final-sale rules, condition rules, and the approved refund, exchange, or store-credit outcomes. The source instruction depends on these rules.
Order reference
The source asks for an order number or ID. Prepare the minimum order information needed to verify the case before asking the model to draft a response.
Actual return-logistics information
Provide the approved label process, carrier or drop-off details, and the real refund timing. The source text can format these instructions but cannot look them up.
Approved recovery offer
The source includes a discount or recovery offer. Supply a code and terms that are currently approved for the relevant customer and return scenario.
No installation needed
Copy and paste into a model chat
- Expand and copy the complete original Skill.md below.
- Open a new conversation in a compatible AI model, then paste it into the chat box.
- Add verified task details, run one low-risk example, and review the result before using it in store operations.
Original Skill.md
The complete source is shown below. Copy it from the top right to use it.
You are a returns and refund processing assistant for a Shopify store. Follow this workflow:
STEP 1 — ELIGIBILITY CHECK:
Ask for order number. Check against return policy:
- Within 30 days? → Eligible
- Items unopened/unused? → Full refund
- Items opened but undamaged? → Store credit
- Final sale items? → Politely decline
STEP 2 — REASON COLLECTION:
Ask: "What's the reason for the return?" Options:
- Wrong size/fit
- Not as described
- Damaged on arrival
- Changed mind
- Other (free text)
STEP 3 — RESOLUTION:
Based on reason:
- Wrong size → Offer exchange first
- Damaged → Express apology, offer full refund + discount code
- Changed mind → Offer store credit (higher value)
- Not as described → Escalate to quality team
STEP 4 — LOGISTICS:
Generate return instructions:
- Return label (provide link or instructions)
- Drop-off locations nearby
- Expected refund timeline (3-5 business days after received)
STEP 5 — RETENTION:
End with: "While you wait for your refund, here's 15% off your next order: [CODE]. We'd love another chance to get it right!"
Your tone is empathetic and efficient. Never argue with the customer about return reasons.Get started
Starter prompts for the main use cases—copy and use them directly.
01Start with one real task
Do not begin with a store-wide rollout. Pick one reversible task where Returns & Refund Processing Assistant can help you handle customer questions, retention signals, and follow-up work. Use this when the input boundary, owner, and one primary measure from resolution quality, reopen rate, response time, and customer satisfaction are written down.
Show prompt and variablesHide prompt and variables
Start with one real task
Do not begin with a store-wide rollout. Pick one reversible task where Returns & Refund Processing Assistant can help you handle customer questions, retention signals, and follow-up work. Use this when the input boundary, owner, and one primary measure from resolution quality, reopen rate, response time, and customer satisfaction are written down.
Use the Skill above to help me with this task: Start with one real task.
Task details: [TASK_DETAILS]
Constraints or policies to follow: [CONSTRAINTS]
Do not begin with a store-wide rollout. Pick one reversible task where Returns & Refund Processing Assistant can help you handle customer questions, retention signals, and follow-up work.
Return a practical result and clearly flag anything that needs human review.Replace these variables
[CODE]- Replace this placeholder with your verified store-specific information.
02Prepare the input and guardrails
Collect only the current policies, representative conversations, order context, and escalation rules needed for this test. Remove unrelated personal data and state which actions must never run automatically. Use this when every input has a known source, sensitive fields are minimized, and the approver knows what the trial can read or change.
Show prompt and variablesHide prompt and variables
Prepare the input and guardrails
Collect only the current policies, representative conversations, order context, and escalation rules needed for this test. Remove unrelated personal data and state which actions must never run automatically. Use this when every input has a known source, sensitive fields are minimized, and the approver knows what the trial can read or change.
Use the Skill above to help me with this task: Prepare the input and guardrails.
Task details: [TASK_DETAILS]
Constraints or policies to follow: [CONSTRAINTS]
Collect only the current policies, representative conversations, order context, and escalation rules needed for this test. Remove unrelated personal data and state which actions must never run automatically.
Return a practical result and clearly flag anything that needs human review.Replace these variables
[CODE]- Replace this placeholder with your verified store-specific information.
03Inspect the source Skill, then run it
Read the source, installation method, and permission notes before adding Returns & Refund Processing Assistant to a separate test project. Keep commands and Skill text exactly as published. Use this when you have a customer-service or retention workflow that a responsible operator can inspect, and it stayed inside the approved boundary.
Show prompt and variablesHide prompt and variables
Inspect the source Skill, then run it
Read the source, installation method, and permission notes before adding Returns & Refund Processing Assistant to a separate test project. Keep commands and Skill text exactly as published. Use this when you have a customer-service or retention workflow that a responsible operator can inspect, and it stayed inside the approved boundary.
Use the Skill above to help me with this task: Inspect the source Skill, then run it.
Task details: [TASK_DETAILS]
Constraints or policies to follow: [CONSTRAINTS]
Read the source, installation method, and permission notes before adding Returns & Refund Processing Assistant to a separate test project. Keep commands and Skill text exactly as published.
Return a practical result and clearly flag anything that needs human review.Replace these variables
[CODE]- Replace this placeholder with your verified store-specific information.
04Review it against a baseline
Do not judge the result by fluency. Compare it with source data, the current SOP, and the pre-test baseline; record factual errors, omissions, and editing time. Use this when resolution quality, reopen rate, response time, and customer satisfaction has a pre-test baseline, and errors and exceptions are logged separately.
Show prompt and variablesHide prompt and variables
Review it against a baseline
Do not judge the result by fluency. Compare it with source data, the current SOP, and the pre-test baseline; record factual errors, omissions, and editing time. Use this when resolution quality, reopen rate, response time, and customer satisfaction has a pre-test baseline, and errors and exceptions are logged separately.
Use the Skill above to help me with this task: Review it against a baseline.
Task details: [TASK_DETAILS]
Constraints or policies to follow: [CONSTRAINTS]
Do not judge the result by fluency. Compare it with source data, the current SOP, and the pre-test baseline; record factual errors, omissions, and editing time.
Return a practical result and clearly flag anything that needs human review.Replace these variables
[CODE]- Replace this placeholder with your verified store-specific information.
Risks and operating notes
Use the current return policy, not the example rule
The instruction includes example eligibility and resolution paths. Replace its time window, final-sale handling, refund, exchange, and store-credit rules with the policy that is currently approved for your store.
Do not invent labels, links, locations, or timelines
This text can draft return instructions, but it does not verify a carrier label, local drop-off point, parcel status, or refund-processing time. Use only details supplied by your actual return system.
Only offer approved recovery incentives
The instruction may suggest an exchange, store credit, or discount code. Confirm the offer amount, eligibility, stacking rules, and margin impact before it is sent to a customer.
A chat instruction does not update inventory
If the instruction mentions inventory, treat that as an operational step to verify. A pasted Skill cannot change stock records unless a separately configured and approved integration performs that action.
Network-collected; original author unavailable.
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.
Risk, permissions, and limitations
Review third-party permission scopes before providing store data. Never paste payment credentials, customer passwords, or unnecessary personal data into a model. Outputs must be checked by the operator responsible for the workflow.
Content checked:
No reviews yet.