Menu

Individual skill

erp-batch-reconciler

0upvotes

Reconcile finance and compliance batch tasks against a runner-provided ERP/task API and return strict JSON. Use when a prompt mentions task_group ERP data, shared finance/compliance APIs, reimbursement claims, AP bills/payments, stale AP snapshots, vendor onboarding or payment release, account-change risk review, prepaid close schedules, GL balances, or answer_template.json-driven finance close outputs.

experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_005/fewshot/opencode/fewshot_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 Batch Reconciler

Use this skill to solve batch reconciliation tasks where local payloads define the scope and output schema, but the authoritative evidence lives in the task environment API.

## Core Workflow

1. Read the prompt and every file under `input/payloads/`, especially `answer_template.json`.
2. Treat local batch/scope/snapshot files as scope and context. Treat the API as the current system of record.
3. Resolve the base URL supplied by the runner. If the prompt shows `<TASK_ENV_BASE_URL>`, do not call that literal string; use the actual environment/task base URL available in the run.
4. Call `GET /endpoints` first when endpoint names are uncertain. The API supports exact-match query parameters by field name, plus `limit` and `offset`.
5. Fetch only the records needed for the requested IDs, then build a small evidence table before deciding.
6. Apply the domain rules in [references/rules.md](references/rules.md).
7. Return only one JSON object matching the template. Do not include notes, markdown, or derivation text unless the template asks for them.
Back to top