Menu

Individual skill

erp-finance-review

0upvotes

Cross-reference ERP finance REST API endpoints with local batch payloads to produce classification, reconciliation, and risk-review decisions formatted to strict JSON answer templates.

experiments/codex_skill_creator_comparison_deepseek_v4_pro_max/reports/skills/task_group_005/fewshot/naive/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
Yes
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 Batch Review

Use this skill when a task asks you to review a batch of claims, vendors, invoices, or account-change events against a shared ERP/compliance REST API and produce a JSON answer that conforms to a provided template. The pattern appears in four task families: claim-AP reconciliation, vendor compliance onboarding, prepaid close reconciliation, and stale-export refresh with account-change risk review.

## Core Workflow

Every task in this family follows the same skeleton. Follow it exactly, adapting only the endpoints and business rules to the task type.

1. **Read the answer template first.** The template file (usually `input/payloads/answer_template.json`) defines required keys, allowed enum values, ordering constraints, and field types. Every output must satisfy every constraint in the template.

2. **Read local payloads.** These provide the batch scope (claim IDs, business IDs, invoice IDs) and optionally context like stale snapshots or review notes. Local payloads are context, not system of record -- the API is always authoritative for current state.

3. **Use the API base URL from `<TASK_ENV_BASE_URL>`.** The runner injects this value. Do not hardcode it. The API supports dual-path routing: a short path (e.g. `/claims`) and a `/api/`-prefixed path (e.g. `/api/claims`). Try one and fall back to the other if the first returns an empty result or a 404. Both paths return the same schema.
Back to top