Individual skill

erp-finance-control-review

Use this skill for task_group_005 ERP finance API tasks, especially reimbursement-to-AP close reviews, stale AP batch refreshes, vendor onboarding or account-change release controls, prepaid close reconciliations, AP aging, payments, vendors, compliance, claims, bills, GL balances, and close-log checks. Trigger whenever the prompt asks for JSON decisions from the shared ERP finance API, even when local payloads look sufficient, because the API is the system of record and the templates have strict field, ordering, and precision rules.

experiments/codex_gpt5_5_xhigh/reports/skills/task_group_005/self/self_attempt_01/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
121
Repository last updated
Oct 29, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# ERP Finance Control Review

Use this SOP to solve task_group_005 finance-control tasks from the shared API. The common shape is: a prompt gives a narrow batch, local payloads define scope and output shape, and the remote ERP API supplies current evidence. Local exports can be stale context; do not treat them as authoritative unless the prompt explicitly asks you to compare against them.

## First Pass

1. Read the prompt, every local input payload, and the answer template before querying. Extract:
   - Target IDs only: claim IDs, business IDs, invoice IDs, accounts, periods, entity, as-of date, review date, thresholds, and batch IDs.
   - Required top-level keys, enum values, list ordering, and numeric precision.
2. Use the runner-provided API base URL. If an environment note is present, prefer that value over prompt examples such as localhost. Do not read local environment source or data directories.
3. Start with `/health`, `/api/health`, or `/endpoints` if the API shape is uncertain. Object-list endpoints return `count`, `data`, `limit`, `offset`, and `total`.
4. Query only the scoped records. Endpoints support exact-match query parameters by field name plus `limit` and `offset`.
5. Treat current API records as the source of truth. Use local CSV or JSON snapshots only for scope, ticket context, stale-row correction labels, or requested metadata.
6. Keep evidence categories separate in your notes: