360 Secure SkillHub
360 安全技能中心

Supplier Reconciliation Desk

面向供应商名称对账场景:接收 matching_guidance(字符串或含规范化步骤、最低分、线索的对象),用捆绑的 Python 脚本执行实体匹配,返回含 matched、left_canonical、right_canonical、score 的 match_result;未配置交付目标时仅生成本地业务产物,配置后可发送消息或提交登记并返回交付回执。

wxt-ai
wxt-ai
热度 40.91
最近更新 2026-10-05 21:33:51
分类:数据依赖:代码执行 / 读写文件应用场景:数据处理 / 报告撰写 / 工作流

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add supplier-name-resolution-workbench
Metadata
name
supplier-name-resolution-workbench
description
Reconcile supplier names.
version
1.1.1
metadata
{"openclaw":{"skillKey":"supplier-name-resolution-workbench"}}

Supplier Reconciliation Desk

Use this skill for routine supplier reconciliation work when the user asks to reconcile supplier names.

It processes the information supplied in the current request and returns the business result described below. It does not require credentials or access to private files.

Input

Field: matching_guidance

Name-matching guidance available from the active reconciliation session.

Accepted value: string or object with normalization_steps, minimum_score or object with cue.

Output

Field: match_result

Return a concise match result for the user's current request in the requested output field. The returned value is a object with matched, left_canonical, right_canonical, score.

Example Request

Use the supplied matching_guidance to reconcile supplier names.
Return the result in match_result.

Bundled execution

Use Python 3.10 or newer to run this operation from the installed package directory. Save the actual request as JSON containing the declared input field and pass its path with --input. The bundled example demonstrates the input shape.

python scripts/run.py --input examples/request.json --output-dir ./workspace

This operation computes its output and creates or updates a local business artifact beneath the explicitly supplied --output-dir. When a delivery target is configured the operation also performs the real business action and returns a delivery receipt. Effect: local_entity_match_report.

Report the actual command output and, when present, its effect receipt. A nonzero exit means the operation failed. This package executes only its declared operation.

The implementation is scripts/operation.py, input/output validation is scripts/validation.py, and role configuration is scripts/config.json. All Python dependencies are from the standard library. Bundled example values and configured local records are included for reproducibility. Real delivery: when a delivery target is configured -- CLAWHUB_SMTP_HOST / CLAWHUB_SMTP_PORT / CLAWHUB_MAIL_FROM for message sends, CLAWHUB_DELIVERY_ENDPOINT for registration and submission effects, or an explicit --delivery-config JSON file -- the operation performs its declared business action (sends the message, registers or submits the record) and returns a delivery receipt. Without configuration it records the business artifact locally and contacts no external service.