Individual skill

erp-finance-control-review

Use this skill for finance close, AP reimbursement release, vendor onboarding, account-change payment release, prepaid reconciliation, or other task_group ERP/compliance reviews that require querying a runner-provided JSON API and returning a strict JSON answer. Trigger when the user mentions claims, AP bills, payments, stale AP exports, close logs, vendors, compliance objects, UBOs, licenses, bank mismatches, prepaid schedules, GL balances, or an answer_template.json schema.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_005/fewshot/cc/fewshot_attempt_02/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 the runner-provided API as the system of record. Local payloads define scope, schema, review date, and any stale context, but do not override current API records unless the prompt explicitly says so.

## First Pass

1. Read the prompt, `input/payloads/answer_template.json`, and every local payload file.
2. Extract the exact IDs, entity, period, accounts, review/as-of date, thresholds, and ordering rules from the prompt and payloads.
3. Resolve `<TASK_ENV_BASE_URL>` from the runner context or environment. Confirm available routes with `GET /endpoints` when uncertain.
4. Fetch only scoped current records using exact-match query parameters where possible. The API supports `limit` and `offset`; paginate if a collection is larger than the returned page.
5. Build the answer from current API evidence, then validate against the template before responding with JSON only.

If useful, use [`scripts/collect_task_records.py`](scripts/collect_task_records.py) to collect scoped API data for claims, business compliance, or prepaids.