为实时语音评估选择合适的共享运行框架,创建提示词、工具定义、初始数据和README,再通过少量样例运行、完整评估及测试验证配置。
- 开始单轮语音评估
- 准备使用已保存音频的评估
- 构建含模拟工具响应的多轮评估
按付款政策检查发票、费用收据和服务合同,在人工批准前识别金额差异、凭证缺失及合同风险,并以JSON报告记录问题和审核结论。
Review invoices and contracts against accounts-payable policy before human approval.
实测评分 未实测
查看安装方法该技能按照付款政策AP-104检查发票、费用收据和服务合同,并生成JSON报告。它提取发票全部明细的数量与单价,复算小计及含运费总额,报告与标示总额的差值。还会检查采购订单等批准记录、缺失收据、无依据的收费和付款指示变更。合同检查会阅读全部条款,报告自动续约、解约期限限制、单方面涨价,以及责任上限或保密条款缺失等风险。
适合在人工批准付款或合同前,找出计算错误、资料缺失和需要复核的条款,并区分应补充信息、提交上级复核,还是进入等待批准的阶段。
金额计算使用Python的decimal.Decimal,报告保存至/workspace/output/<document-stem>.json。问题须用通俗英语字符串记录。该技能不会批准付款、签署合同或执行外部操作。即使没有剩余问题,仍须人工批准。
本介绍由 AI(OpenAI Codex)根据公开的 SKILL.md 撰写。准确的规格请查看下方原文。
AI 根据 SKILL.md 的内容检查了需要注意的操作和使用前提。评分只依据实际运行的结果(实测对比)。
不计入评分。 由 AI(OpenAI Codex)于 2026年10月23日 评估。仅供参考,安装前请同时查看原文。
安装前可以查看交给 AI 代理的指令内容。
Policy ID: AP-104.
Apply this policy to invoices, expense receipts, and service contracts.
decimal.Decimal to multiply quantities by unit prices and sum the line totals. Compare this subtotal with the printed subtotal, then add shipping to calculate the total.Total amount due, and report the exact difference (stated total minus calculated total).needs_info: Required documentation or supporting information is missing.escalated: Fraud indicators, financial discrepancies, or risky terms need review.ready_for_approval: No policy violations remain, but a human must still approve.Write /workspace/output/<document-stem>.json with the following fields:
{
"document": "invoice.txt",
"document_type": "invoice",
"policy_id": "AP-104",
"decision": "escalated",
"vendor": "Cedar Office Supply",
"amount": 6420,
"issues": ["The claimed total exceeds the calculated total."],
"recommendation": "Escalate for human review.",
"calculation": {
"line_items": [{"quantity": 2, "unit_price": 100}],
"shipping": 20,
"calculated_total": 220,
"difference": 6200
}
}
Every issues entry must be a plain-English string, not a nested object.
Use the actual document values, not the illustrative numbers above. Include every
invoice line item in calculation; amount is the stated total. For contracts,
set document_type to contract and calculation to null.
Only the coordinator writes summary.json. A specialist writes its assigned report.
Never approve payments, sign contracts, or take external actions.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
为实时语音评估选择合适的共享运行框架,创建提示词、工具定义、初始数据和README,再通过少量样例运行、完整评估及测试验证配置。
审阅OpenAI Cookbook技术文档与笔记本说明文字,核对技术准确性、表述清晰度及发布元数据,以最小改动修正明显问题,并报告需要判断的事项。