shopify-admin-split-shipment-planner
Splits a multi-line fulfillment order into separate shipments for partial or location-specific shipping.
What this skill does
## Purpose
Splits a fulfillment order containing multiple line items into two or more separate fulfillment orders, each of which can be shipped independently with its own tracking number. Used when items in an order ship from different locations, on different dates, or require different carriers. Replaces manual split-shipment handling in Shopify Admin.
## Prerequisites
- Authenticated Shopify CLI session: `shopify store auth --store <domain> --scopes read_orders,write_fulfillments`
- API scopes: `read_orders`, `write_fulfillments`
- Target fulfillment order must be in `OPEN` status
## Parameters
| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| store | string | yes | — | Store domain (e.g., mystore.myshopify.com) |
| fulfillment_order_id | string | yes | — | GID of the fulfillment order to split |
| split_groups | array | yes | — | List of `{line_item_ids: [], quantities: []}` defining each shipment group |
| dry_run | bool | no | true | Preview split without executing mutation |
| format | string | no | human | Output format: `human` or `json` |
## Safety
> ⚠️ `fulfillmentOrderSplit` is irreversible — a split fulfillment order cannot be merged back. The original fulfillment order is replaced by multiple new ones. Run with `dry_run: true` to confirm the intended groupings before committing. Ensure all `line_item_ids` in `split_groups` belong to the target fulfillment order.
## Workflow Steps
1. **OPERATION:** `fulfillmentOrders` — query
**Inputs:** Query for the specific fulfillment order by order ID, filter by `status: OPEN`
**Expected output:** Fulfillment order with all `lineItems { id, remainingQuantity, variant { sku, title } }`
2. Validate `split_groups` — confirm all line item IDs exist in the fulfillment order and quantities are ≤ remaining quantities
3. **OPERATION:** `fulfillmentOrderSplit` — mutation
**Inputs:** `fulfillmentOrderId`, `fulfillmentOrderLineItems` array per split group
**Expected output:** Array of new `fulfillmentOrders { id, lineItems }`, `userErrors`
## GraphQL Operations
```graphql
# fulfillmentOrders:query — validated against api_version 2025-01
query FulfillmentOrderLines($orderId: ID!) {
order(id: $orderId) {
id
name
fulfillmentOrders(first: 10) {
edges {
node {
id
status
lineItems(first: 50) {
edges {
node {
id
remainingQuantity
totalQuantity
variant {
id
sku
title
}
}
}
}
}
}
}
}
}
```
```graphql
# fulfillmentOrderSplit:mutation — validated against api_version 2025-01
mutation FulfillmentOrderSplit($fulfillmentOrderId: ID!, $fulfillmentOrderLineItems: [FulfillmentOrderLineItemInput!]!) {
fulfillmentOrderSplit(
fulfillmentOrderId: $fulfillmentOrderId
fulfillmentOrderLineItems: $fulfillmentOrderLineItems
) {
fulfillmentOrders {
id
status
lineItems(first: 50) {
edges {
node {
id
remainingQuantity
variant {
sku
title
}
}
}
}
}
userErrors {
field
message
}
}
}
```
## Session Tracking
**Claude MUST emit the following output at each stage. This is mandatory.**
**On start**, emit:
```
╔══════════════════════════════════════════════╗
║ SKILL: Split Shipment Planner ║
║ 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>
```
If `dry_run: true`, prefix every mutation step with `[DRY RUN]` and do not execute it.
**On completion**, emit:
For `format: human` (default):
```
══════════════════════════════════════════════
OUTCOME SUMMARY
Original fulfillment order: <id>
Split into: <n> shipments
Errors: <n>
Shipment 1: <line items summary>
Shipment 2: <line items summary>
══════════════════════════════════════════════
```
For `format: json`, emit:
```json
{
"skill": "split-shipment-planner",
"store": "<domain>",
"started_at": "<ISO8601>",
"completed_at": "<ISO8601>",
"dry_run": true,
"original_fulfillment_order_id": "<id>",
"resulting_fulfillment_orders": [],
"errors": 0
}
```
## Output Format
Human-readable split summary. No CSV output — split results are viewable in Shopify Admin under the order's fulfillment tab.
## Error Handling
| Error | Cause | Recovery |
|-------|-------|----------|
| `THROTTLED` | API rate limit exceeded | Wait 2 seconds, retry |
| `userErrors` — invalid line item | Line item ID not in fulfillment order | Abort and report mismatch |
| `userErrors` — quantity exceeds remaining | Split quantity > remaining quantity | Abort and report per line item |
| Fulfillment order not OPEN | Already fulfilled or cancelled | Abort with status report |
## Best Practices
- Use `dry_run: true` to preview the resulting shipment groups before splitting — a split cannot be reversed.
- Ensure `split_groups` covers all line items in the fulfillment order; any unassigned items will remain in the original (residual) fulfillment order.
- For orders with items shipping from different warehouses, use the `fulfillment-location-routing` skill to move the split groups to the correct locations after splitting.
Related in Productivity
gitea-workflow
IncludedOrchestrate agile development workflows for Gitea repositories using the tea CLI. Use when working with Gitea-hosted repos and asking to 'run the workflow', 'continue working', 'what's next', 'complete the task cycle', 'start my day', 'end the sprint', 'implement the next task', or wanting guided step-by-step development assistance. Keywords: workflow, orchestrate, agile, task cycle, sprint, daily, implement, review, PR, standup, retrospective, gitea, tea.
microsoft-graph-gateway
IncludedRoute Microsoft Graph work in this workspace. Use when users want to read or write Outlook mail, calendar events, contacts, OneDrive or SharePoint files, Teams, Planner, To Do, users, groups, directory data, or arbitrary Microsoft Graph endpoints from VS Code. Prefer WorkIQ for common read scenarios. Use Microsoft Graph for write actions and gap-read scenarios that need exact Graph properties, filters, permissions, or endpoints.
copilotkit
IncludedUse when building with CopilotKit — setup, development, integrations, debugging, upgrading, or contributing. Routes to the appropriate specialized skill based on the task.
wordly-wisdom
IncludedProvides calibrated decision analysis using Charlie Munger-style multiple mental models, inversion, incentive mapping, circle-of-competence checks, misjudgment audits, second-order effects, and forecast updates. Use when the user asks for an oracle take, a hard call, a decision memo, a premortem, an outside view, a red-team, a sanity-check, what am I missing, think this through, or wants a strategy, hire, investment, plan, product, partnership, or major life choice analysed. Avoid for simple factual lookups or time-sensitive legal, medical, or market questions without fresh evidence.
swain-session
IncludedSession management and project status dashboard. Owns the full session lifecycle (start/work/close/resume), focus lane, bookmarks, worktree detection, and tab naming. Also serves as the project status dashboard — shows active epics, progress, actionable next steps, blocked items, tasks, GitHub issues, and recommendations. Worktree creation is deferred to swain-do task dispatch (SPEC-195). Triggers on: 'session', 'status', 'what's next', 'dashboard', 'overview', 'where are we', 'what should I work on', 'show me priorities', 'bookmark', 'focus on', 'session info'.
gandi
IncludedComprehensive Gandi domain registrar integration for domain and DNS management. Register and manage domains, create/update/delete DNS records (A, AAAA, CNAME, MX, TXT, SRV, and more), configure email forwarding and aliases, check SSL certificate status, create DNS snapshots for safe rollback, bulk update zone files, and monitor domain expiration. Supports multi-domain management, zone file import/export, and automated DNS backups. Includes both read-only and destructive operations with safety controls.