Individual skill
finance-control-api-review
Reconcile finance-control batches against runner-provided JSON APIs and local answer templates. Use when solving ERP, AP, compliance, vendor onboarding, prepaid close, reimbursement close, stale AP snapshot refresh, or account-change payment release tasks that require a strict JSON decision output.
experiments/codex_skill_creator_comparison_gpt5_5_xhigh/reports/skills/task_group_005/fewshot/deepagents/fewshot_attempt_01/SKILL.md
Source commit 5082a777379156a048881e94940d640702e5e09a
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Local scripts
- 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.
- agent Repository topic
- ai Repository topic
- benchmark Repository topic
- llm Repository topic
- self-evolving Repository topic
- self-learning Repository topic
- skills Repository topic
- legal Derived category
- finance Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 2,983 bytesSKILL.mdcore · 2,983 bytesreferences/control_review_workflows.mddoc · 8,893 bytesscripts/task_api.pyruns · 3,643 bytes
Read excerpt
# Finance Control API Review
## Core Workflow
1. Read the user prompt, the answer template, and every local payload that defines scope. Treat scoped IDs, review dates, periods, thresholds, and required output keys from those files as authoritative.
2. Use the runner-provided task API as the system of record. Query `/endpoints` first when available, prefer `/api/...` endpoints, and fall back to the non-API aliases named by the prompt.
3. Fetch current records with exact-match filters by ID field. Use local snapshots or batch files only as scope/context unless the prompt explicitly says they are authoritative.
4. Build an evidence table per scoped claim, business, invoice, or ticket before deciding. Do not copy source `review_status` values directly into the answer; derive release or close posture from the current evidence.
5. Return only the JSON object requested by the template. Preserve required key names, enum spellings, precision, and ordering. Sort ID lists ascending unless the template says to keep payload order.
## API Helper
Use [scripts/task_api.py](scripts/task_api.py) when repeated API reads would be error-prone:
