Explore in MochiBot. Install in chat.Hosted workspaces and MochiBot lightweight setups include the Skills assistant. Choose a Skill and ask for installation in chat. Other OpenClaw setups can follow the first-install guide.
How to use Skills →
MOCHILAB / AI SKILL
Return Reasons and Operations Backlog
Separate return requests, physical receipts and refunds; report SKU cohort rates, reasons and unfinished work.
What it does
Separate return requests, physical receipts and refunds; report SKU cohort rates, reasons and unfinished work.
Model and scope
order_lines contain unique line_id, sku, currency, ordered_at, gross ordered quantity and canceled quantity. returns contain unique return_id, linked line_id, requested_at, quantity, received_quantity, nullable received_at/closed_at, reason and explicit refund_expected boolean. Each return row is one lifecycle snapshot, not repeated cumulative snapshots. Cumulative requested units must not exceed uncanceled order units. refunds contain unique refund_id, line_id, optional return_id, occurred_at, quantity, nonnegative amount and matching currency. Separate refund records are incremental, not cumulative snapshots. Cutoff filters future request/refund/receipt/closure stages. Physical rate = physically received / gross ordered units in the supplied order cohort; show canceled units separately. Refund gaps compare only linked units for explicit refund_expected, without determining legal or monetary entitlement. Amount totals stay separate by currency. No inferred refund-to-return matching.
Try saying
Reconcile physical returns and linked refunds, keeping cancellations separate from the return-rate denominator.
List open returns by age and flag received units with an explicitly expected refund still unmatched.
Runtime and outputs
Reads supplied normalized JSON and creates result.json, report.md and rows.csv with input and output hashes. Preserve raw CSV; ask the assistant to normalize exports against the bundled input reference. Python 3.10+ standard library only; no paid data key or MochiLab backend needed. Optional explanation uses your current agent model and its ordinary service costs separately. Existing output directories are refused. Includes fictional examples and independent offline domain tests. No API/store changes, uploads, automatic tasks, notifications, legal or tax decisions.
References