Return Intake
Purpose
Assemble the case facts: request, order record, SKU attributes, customer return history. Entry hop of every return case.
When to use
- Start of every return case ("customer wants to return", "start a return case", "log this return").
When NOT to use
- Deciding eligibility, refund or red flags - eligibility-check owns the determination.
- Fetching policy clauses or windows - policy-retrieve.
- Classifying the reason code - reason-classify.
- Drafting the packet, customer response or manager exception request - case-packet.
Where the data comes from
This plugin ships no sample data. Every input is the user's own Microsoft 365 content:
- Facts the user types in the chat, and files the user names, links or attaches (a service-desk note, a customer email, an order/receipt lookup export, a customer return-history export).
- Their OneDrive or SharePoint, found with Work IQ search (Microsoft 365 search) by case ID, order ID, unit serial or file name when no location is given.
- Email attachments or the customer's email itself, found the same way.
Read each source with the file reader (ReadFileContent) and cite it by file name and row (CSV exports carry a row column) or by line/section for notes and emails. Write the working JSON file (case.json) to the session working folder, never into the plugin. If a required source cannot be found, say which one is missing and ask the user where it is. Never invent it, estimate it or fall back to example values.
Inputs
Configuration ships inside this skill folder (synced from the plugin-root shared/ copy before packaging): config/, contracts/, references/returns-rules.md - paths below are relative to this skill folder. Case facts come from the user's Microsoft 365 content (see Where the data comes from):
- The request as stated: the service-desk note, customer email or chat message (verbatim reason text, item, category, value, receipt presented, condition flags, unit serial, request date).
- The order/receipt lookup export: order ID, order date, category, unit price, sold serial.
- The customer return-history export: receiptless returns in the last 90 days.
Schema: contracts/rtl.returns-refund-case.v1.json.
Steps
- Find and read the sources above; list which were found and which are missing.
- Mint
case_id as RET-<YYYY>-<5-digit sequence> (contract convention); never encode the order id or customer identity in it. If the note, email or user already gives a case ID, use that one.
- Capture
reason_text verbatim - classification and the human exception path depend on the actual words.
- Build
case.json in the session working folder in exactly this shape (values below are neutral placeholders, not data):
{ "contract_version": "rtl.returns-refund-case.v1", "case_id": "RET-2000-00001",
"return_request": {"category": "<config/return-windows.json windows_days key>", "value": 0.0, "has_receipt": true,
"opened": null, "worn": null, "requested_on": "YYYY-MM-DD", "reason_text": "<verbatim>", "unit_serial": null,
"item": "<as described>", "citation": "<note or email file name, line>"},
"order": {"order_id": "ORD-0000-EXAMPLE", "order_date": "YYYY-MM-DD", "sold_serial": null, "citation": "<export file name, row n>"},
"customer_history": {"receiptless_returns_90d": 0, "citation": "<export file name, row n>"},
"escalations": [] }
Record category, value, has_receipt, opened, worn, requested_on, unit_serial as presented (a flag the sources do not state -> null or left out, never guessed). Attach order only when the lookup export has the order (with order_date and sold_serial), and customer_history only when the history export has the customer; each with a citation.
5. Validate against the contract (required keys, contract_version const, case_id pattern); write case.json to the session working folder.
Example
User: "Customer wants to return a $120 bluetooth headset, no receipt; the desk found order ORD-0000-EXAMPLE."
-> ReadFileContent: order/receipt lookup export (ORD-0000-EXAMPLE, order date, sold serial SN-EXAMPLE-1) - cite file + row
-> ReadFileContent: customer return-history export (receiptless_returns_90d) - cite file + row
-> write case.json (session folder): case_id RET-2000-00001, reason_text verbatim, has_receipt false, unit_serial SN-EXAMPLE-2
Reply: "Case RET-2000-00001 recorded. Order and history attached (sources cited); receipt not presented. No determination made."
Output format
case.json - the entry hop: {contract_version, case_id, return_request{...}, order?{...}, customer_history?{...}, escalations: []}. No reason, eligibility or fraud_signals keys. Tell the user which records were found and which are missing.
Grounding requirements
Every fact cites its record (order id, POS receipt, history extract). The story is recorded; it is not evidence.
Guardrails
- Never fabricate a fact to complete the record; write
null or leave the block absent and cite what was searched.
- No eligibility or fraud opinions here - record the serial mismatch or the return count as facts only.
- Never fabricate an order id, date or history value; if the lookup finds nothing, leave the block absent and record it in
escalations.
- Never skip the history pull because the customer is friendly - it is part of every case.
- Draft-first: nothing here approves, refunds or declines anything.
Escalation / uncertainty
If the order lookup export or the history export cannot be found or returns nothing: record the block as absent, add an escalations entry naming the missing record, ask the user for it (for example the order number and purchase date from the receipt), and never fabricate a stand-in value.
No order found and no receipt: record it; the Govern step (eligibility-check) decides what that means. Ambiguous category: ask the user before writing.
1---2name: return-intake3description: 'Structures a customer return request - item, order/receipt, reason as stated, condition, serials, customer history - into the rtl.returns-refund-case.v1 contract as case.json. Use when the user says "customer wants to return", "process this return", "start a return case", "log this return", "new return at the desk", or a return case begins. Do NOT use for eligibility or refund decisions - use eligibility-check instead; not for policy text - use policy-retrieve; not for the write-up or customer response - use case-packet.'4license: Proprietary5metadata:6 source: https://skillmd.com/skills/microsoft/return-intake7 version: 1.0.48 author: Microsoft Retail & CPG Skills9 category: productivity10 icon: Form11---1213# Return Intake14## Purpose15Assemble the case facts: request, order record, SKU attributes, customer return history. Entry hop of every return case.16## When to use17- Start of every return case ("customer wants to return", "start a return case", "log this return").18## When NOT to use19- Deciding eligibility, refund or red flags - eligibility-check owns the determination.20- Fetching policy clauses or windows - policy-retrieve.21- Classifying the reason code - reason-classify.22- Drafting the packet, customer response or manager exception request - case-packet.23## Where the data comes from24This plugin ships no sample data. Every input is the user's own Microsoft 365 content:25- Facts the user types in the chat, and files the user names, links or attaches (a service-desk note, a customer email, an order/receipt lookup export, a customer return-history export).26- Their OneDrive or SharePoint, found with Work IQ search (Microsoft 365 search) by case ID, order ID, unit serial or file name when no location is given.27- Email attachments or the customer's email itself, found the same way.2829Read each source with the file reader (ReadFileContent) and cite it by file name and row (CSV exports carry a `row` column) or by line/section for notes and emails. Write the working JSON file (`case.json`) to the session working folder, never into the plugin. If a required source cannot be found, say which one is missing and ask the user where it is. Never invent it, estimate it or fall back to example values.3031## Inputs32Configuration ships inside this skill folder (synced from the plugin-root shared/ copy before packaging): `config/`, `contracts/`, `references/returns-rules.md` - paths below are relative to this skill folder. Case facts come from the user's Microsoft 365 content (see *Where the data comes from*):33- The request as stated: the service-desk note, customer email or chat message (verbatim reason text, item, category, value, receipt presented, condition flags, unit serial, request date).34- The order/receipt lookup export: order ID, order date, category, unit price, sold serial.35- The customer return-history export: receiptless returns in the last 90 days.36Schema: contracts/rtl.returns-refund-case.v1.json.37## Steps381. Find and read the sources above; list which were found and which are missing.392. Mint `case_id` as `RET-<YYYY>-<5-digit sequence>` (contract convention); never encode the order id or customer identity in it. If the note, email or user already gives a case ID, use that one.403. Capture `reason_text` verbatim - classification and the human exception path depend on the actual words.414. Build `case.json` in the session working folder in exactly this shape (values below are neutral placeholders, not data):42```json43{ "contract_version": "rtl.returns-refund-case.v1", "case_id": "RET-2000-00001",44 "return_request": {"category": "<config/return-windows.json windows_days key>", "value": 0.0, "has_receipt": true,45 "opened": null, "worn": null, "requested_on": "YYYY-MM-DD", "reason_text": "<verbatim>", "unit_serial": null,46 "item": "<as described>", "citation": "<note or email file name, line>"},47 "order": {"order_id": "ORD-0000-EXAMPLE", "order_date": "YYYY-MM-DD", "sold_serial": null, "citation": "<export file name, row n>"},48 "customer_history": {"receiptless_returns_90d": 0, "citation": "<export file name, row n>"},49 "escalations": [] }50```51 Record `category`, `value`, `has_receipt`, `opened`, `worn`, `requested_on`, `unit_serial` as presented (a flag the sources do not state -> `null` or left out, never guessed). Attach `order` only when the lookup export has the order (with `order_date` and `sold_serial`), and `customer_history` only when the history export has the customer; each with a `citation`.525. Validate against the contract (required keys, `contract_version` const, `case_id` pattern); write `case.json` to the session working folder.53## Example54```55User: "Customer wants to return a $120 bluetooth headset, no receipt; the desk found order ORD-0000-EXAMPLE."56-> ReadFileContent: order/receipt lookup export (ORD-0000-EXAMPLE, order date, sold serial SN-EXAMPLE-1) - cite file + row57-> ReadFileContent: customer return-history export (receiptless_returns_90d) - cite file + row58-> write case.json (session folder): case_id RET-2000-00001, reason_text verbatim, has_receipt false, unit_serial SN-EXAMPLE-259Reply: "Case RET-2000-00001 recorded. Order and history attached (sources cited); receipt not presented. No determination made."60```61## Output format62`case.json` - the entry hop: `{contract_version, case_id, return_request{...}, order?{...}, customer_history?{...}, escalations: []}`. No `reason`, `eligibility` or `fraud_signals` keys. Tell the user which records were found and which are missing.63## Grounding requirements64Every fact cites its record (order id, POS receipt, history extract). The story is recorded; it is not evidence.65## Guardrails66- Never fabricate a fact to complete the record; write `null` or leave the block absent and cite what was searched.67- No eligibility or fraud opinions here - record the serial mismatch or the return count as facts only.68- Never fabricate an order id, date or history value; if the lookup finds nothing, leave the block absent and record it in `escalations`.69- Never skip the history pull because the customer is friendly - it is part of every case.70- Draft-first: nothing here approves, refunds or declines anything.71## Escalation / uncertainty72If the order lookup export or the history export cannot be found or returns nothing: record the block as absent, add an `escalations` entry naming the missing record, ask the user for it (for example the order number and purchase date from the receipt), and never fabricate a stand-in value.73No order found and no receipt: record it; the Govern step (eligibility-check) decides what that means. Ambiguous category: ask the user before writing.