---
name: br-inv-cost-close-readiness
description: >
  Assess Oracle EBS Inventory/Costing period-close readiness in Excel: have the
  br-run-reports skill extract pending inventory transactions, missing WIP/receiving
  accounting, and pending cost adjustments, then give a red/amber/green verdict with remediation
  and build an Inventory close-readiness scorecard. Use when the user asks "can we close
  inventory for {period}", "inventory/costing period close readiness", pending/uncosted
  transactions, stuck MTL interfaces, or missing accounting.
# Trigger: Slash command + auto
---

# Inventory / Costing Period Close Readiness (br-inv-cost-close-readiness)

> 🚨 **Blitz data = Excel worksheet UDFs, not MCP tools/connectors.** Extract data only by writing `=br_...()` into a cell (via `execute_office_js`) and reading the spill — **never** `tool_search` for `br_*`, **never** `refresh_mcp_connectors`, and never conclude "no Oracle EBS / Blitz connector is set up" (the Blitz Report add-in is an Excel add-in, not an MCP connector, so it never appears in the connector list — its absence there is expected). Load the extraction mechanism first: `read_skill("br-run-reports")`.


> **Performance:** Read `br-analytics-standards` at the start of every run
> (`read_skill("br-analytics-standards")`). All pipeline steps must follow those rules.
> Target runtime: under 7 minutes for single-module, under 20 minutes for orchestrations.

Produce an inventory/costing close-readiness scorecard in one workbook. You own orchestration,
scoring, and the verdict; br-run-reports does extraction and br-data-dashboard the
build. Run steps in order, on separate turns, keeping intermediate sheets.

**Requires:** br-run-reports, br-data-dashboard.

## Division of responsibility — READ FIRST
**You do NOT run Blitz reports yourself.** All extraction is done by **br-run-reports**
(connection, auth, async run, completion, cell population). Never call `br_*` functions, and never
rename/read/sum the result sheet or start analysis until extraction is confirmed complete —
touching the workbook mid-run stalls it. This skill is **read-and-recommend only**: it never runs
the cost manager, resubmits interfaces, or uploads; it reports blockers and the recommended action.

## When to use
"Can we close inventory for May", "costing period close readiness", pending/uncosted material
transactions, stuck MTL_TRANSACTIONS_INTERFACE / pending receiving, missing WIP/receiving
accounting, pending cost adjustments.

## Inputs
- **Organization Code** (one or several; ask which orgs) — required; **Period** (Period From / Period To).

## Reports used (authoritative names — do NOT broad-search for them)
These exact report names are known. When you ask br-run-reports to run one, pass the
**documented name directly** — do NOT run a `br_report_list_external` discovery search first. Inspect
parameters only if you need an exact LOV spelling. **Fallback:** only if a run returns
`#BLITZ_REPORT_NOT_FOUND` (the instance renamed it, or the module isn't installed) do a name search.

| Report (exact name) | Run with | Notes |
|---|---|---|
| `INV Period Close Pending Transactions` | Organization Code + Period | **The verdict driver.** Inventory |
| `CAC Accounting Period Status` | **Functional Area = Inventory** (the param is `Functional Area`, NOT `Application`) + Org/Ledger + Period | Period-status check (Step 1c) — per-org INV period |
| `CAC Missing WIP Accounting Transactions` | Organization Code + Period | Missing-WIP-accounting check |
| `CAC Missing Receiving Accounting Transactions` | Organization Code + Period | Missing-receiving-accounting check |
| `CAC Inventory Pending Cost Adjustment` | Organization Code + Period | Pending cost adjustments |
| `CST Uninvoiced Receipts` / `CST AP and PO Accrual Reconciliation` *(optional)* | Org / Ledger + Period | Accrual recon (Review) |
| `CST Period Close Subinventory Value` *(optional)* | Organization Code + Period | Inventory↔GL tie-out |

## CONFIG
### Checks → class + remediation
| Check (source report) | Class | Remediation |
|---|---|---|
| Pending material transactions / interface backlog (`INV Period Close Pending Transactions`) | **Blocker** | Resolve pending rows; resubmit the relevant interface manager |
| Missing WIP accounting (`CAC Missing WIP Accounting Transactions`) | **Blocker** | Run the **Cost Manager** / create accounting for WIP |
| Missing receiving accounting (`CAC Missing Receiving Accounting Transactions`) | **Blocker** | Run **Create Accounting** for receiving |
| Pending cost adjustments (`CAC Inventory Pending Cost Adjustment`, `CAC ICP PII WIP Pending Cost Adjustment`) | **Blocker** | Process the pending cost adjustment |
| Uninvoiced receipts / accrual recon (`CST Uninvoiced Receipts`, `CST AP and PO Accrual Reconciliation`) | **Review** | Period-end accrual; reconcile to GL |
| Subinventory value vs GL (`CST Period Close Subinventory Value`) | **Review** | Inventory↔GL tie-out |

### Readiness (RAG)
- **Red** — any pending transactions, missing accounting, or pending cost adjustments.
- **Amber** — only Review-class accrual/recon items within materiality.
- **Green** — no pending transactions and all accounting created for the org+period.

### Output sheets & tab order (left to right)
`INV_Close_Readiness` (first), [`Accrual_Recon`], `Missing_Accounting`, `Pending_Transactions` (last).

## Pipeline
1. **Extract — DELEGATE.** br-run-reports runs **"INV Period Close Pending Transactions"** (Organization Code + Period) → `Pending_Transactions`; then **"CAC Missing WIP Accounting Transactions"** and **"CAC Missing Receiving Accounting Transactions"** → `Missing_Accounting`; then **"CAC Inventory Pending Cost Adjustment"** (append). Optionally `CST Uninvoiced Receipts` / `CST AP and PO Accrual Reconciliation` → `Accrual_Recon`. Wait for each; do nothing mid-run. For multiple orgs, run per org and stack.
1c. **Confirm the period is open (recommended).** Delegate to br-run-reports to run **"CAC Accounting Period Status"** (**Functional Area = Inventory** — the param is `Functional Area`, not `Application` — for the Org/Ledger + Period). INV periods are **per-org** — confirm the org(s) you're assessing show **Open**, not Closed or Never Opened. Show the status on the scorecard. If the report isn't found on the instance, note that and proceed (don't block on it).
2. **Anchor.** Record pending-transaction count, missing-accounting count, pending-cost-adj count by org. Clean → Green scorecard.
3. **Score.** Apply CONFIG; rank blockers; attach remediation (which manager/program to run).
4. **Scorecard *(single `execute_office_js` call)*** (delegate to br-data-dashboard if it fires; else build inline). Write all scorecard sections to `INV_Close_Readiness` in one call: RAG banner (org+period); pending by type per org; missing-accounting counts; pending cost adj; blocking-items list. Any charts follow in a second call.
   - **Build mechanics (learned on a real run):** build on a NEW sheet at **position 0** (first tab); leave each report on the sheet br-run-reports created (its report name) — do NOT rename it, the dashboard links to it. **Do NOT use a multi-row `copyToRange`** to fill formula rows (it can latch onto the wrong source box and duplicate headers into the data) — write each row's formula explicitly. After building, scan **beyond** the dashboard's column range, clear any stray cells, and widen amount columns so values don't render as `######`.
5. **Narrative.** ≤5 bullets: overall call, biggest blocker, which org is worst, recommended next program to run.
6. **Arrange tabs + final validation.** Arrange tabs per CONFIG; make `INV_Close_Readiness` active. Only after the scorecard. **Then do the one permitted verification read:** confirm the scorecard's pending-transaction, missing-accounting and pending-cost-adj counts tie to the Step-2 anchor. This is the only explicit re-read allowed in the entire pipeline outside of the anchor step.

## Validation
Scorecard counts tie to the raw sheets; Red only if a Blocker exists.

## Closed-loop (roadmap, not executed here)
Cost Manager / interface resubmit are concurrent submits. This skill recommends; a human runs it.