Individual skill

finance-api-close-review

Solve shared ERP finance API tasks that require JSON-only reimbursement/AP close decisions, stale AP snapshot correction, prepaid amortization and GL reconciliation, vendor onboarding finance-risk release calls, or account-change payment release reviews. Use when a task supplies TASK_ENV_BASE_URL or a local input payload plus an answer_template and asks Codex to reconcile current API evidence into a close, release, hold, block, or exception output.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_005/fewshot/codex/fewshot_attempt_03/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

# Finance API Close Review

## Core Workflow

1. Read the prompt, `input/payloads/answer_template.json`, and every local payload before querying the API. Treat the template as the required output contract.
2. Use the runner-provided API base URL as the source of truth. Local CSV exports or batch payloads identify scope and context; they do not override current API records unless the prompt explicitly says so.
3. Query `/endpoints` first when available. The API supports exact-match query parameters by field name plus `limit` and `offset` pagination.
4. Run `scripts/erp_evidence.py` to gather scoped records and draft calculations:

```bash
python /work/skill/scripts/erp_evidence.py --base-url "$TASK_ENV_BASE_URL" --task-dir .
```

Pass the task root or the directory that contains `prompt.txt`; the helper also detects a child `input/` directory.
Back to top