← Back to Skills Marketplace
dazhanggui

guoguo

by dazhanggui · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
99
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install guoguo
Description
裹裹寄件下单,通过MCP连接裹裹寄件服务创建寄件订单。当用户需要寄件、下单、创建寄件订单、寄快递时使用此skill。触发词:寄件、下单、寄快递、寄件下单、创建订单、裹裹下单。
README (SKILL.md)

裹裹寄件下单

通过 MCP 连接裹裹寄件服务(GUOGUO_SEND_SERVICE),为用户创建寄件订单。

前置检查:自动配置 MCP

每次触发此 skill 时,必须先执行此步骤。

检查当前可用的 MCP tool 列表中是否存在 guoguo_send_server 相关的 tool(如 mcp_guoguo_send_server_GUOGUO_SEND_ORDER_CREATE)。

  • 如果已存在 → 跳过,直接进入下单流程
  • 如果不存在 → 执行自动配置脚本(使用 skill 加载时提供的 Base directory 路径):
bash \x3CBase directory>/setup-mcp.sh

脚本会自动检测 Qoder MCP 配置文件位置(兼容 macOS/Linux),若 guoguo_send_server 未配置则自动添加。配置完成后提示用户刷新 MCP 连接或重启 Qoder 以生效。

下单流程

Step 1: 收集下单信息

向用户收集以下全部必要信息(可一次性询问,也可分步收集):

信息项 说明 示例
下单账号 用户手机号,同时作为 externalUserId 和 externalUserMobile 13800138000
寄件人姓名 senderInfo.name 张三
寄件人电话 senderInfo.mobile 13800138000
寄件人地址 senderInfo.fullAddressDetail,必须是完整地址(省市区+详细地址) 西藏自治区阿里地区札达县托林镇丁丁卡牧场
收件人姓名 receiverInfo.name 李四
收件人电话 receiverInfo.mobile 13900139000
收件人地址 receiverInfo.fullAddressDetail,必须是完整地址 浙江省杭州市余杭区文一西路969号
期望揽收开始时间 appointGotStartTime,必须大于当前时间 2026-04-18 14:00

Step 2: 构造请求参数

调用 MCP tool 时需传入两个参数:requestaccessOption

request 参数模板:

{
    "externalUserId": "\x3C下单账号>",
    "externalUserMobile": "\x3C下单账号>",
    "itemId": 3000000040,
    "itemVersion": 4,
    "senderInfo": {
        "name": "\x3C寄件人姓名>",
        "mobile": "\x3C寄件人电话>",
        "fullAddressDetail": "\x3C寄件人完整地址>"
    },
    "receiverInfo": {
        "name": "\x3C收件人姓名>",
        "mobile": "\x3C收件人电话>",
        "fullAddressDetail": "\x3C收件人完整地址>"
    },
    "timeType": 2,
    "appointGotStartTime": "\x3C期望揽收开始时间,毫秒时间戳>",
    "appointGotEndTime": "\x3CappointGotStartTime + 7200000>",
    "outOrderInfoList": [],
    "designatedDeliveryUserId": null,
    "extensionMap": null,
    "userRemark": null,
    "externalUserType": 5
}

关键计算规则:

  • appointGotStartTime:用户提供的揽收开始时间,转为毫秒时间戳
  • appointGotEndTime:= appointGotStartTime + 7200000(即加 2 小时),此间隔由 itemId 决定,当前 3000000040 固定加 2 小时
  • appointGotStartTime 必须大于当前时间,否则提示用户重新选择

固定值映射表:

itemId itemVersion 服务类型 揽收时间间隔
3000000040 4 两小时服务 +2小时

accessOption 参数(固定值):

{
    "accessCode": "示例",
    "accessMethod": null
}

Step 3: 调用 MCP Tool 下单

调用 guoguo_send_server MCP 服务中的寄件下单 tool,传入上述 request 和 accessOption 两个参数。

Step 4: 处理响应

下单成功result.success"true"):

向用户展示以下信息:

  • 寄件单号result.data.orderId
  • 取件码result.data.gotCode
  • 账号IDresult.data.cnAccountId

成功响应示例:

{
  "result": {
    "data": {
      "externalUserId": "2074370454",
      "orderId": "21240720002375404",
      "cnAccountId": "2074370454",
      "gotCode": "5617"
    },
    "success": "true"
  }
}

下单失败

响应中会包含失败原因,提取并明确告知用户失败原因,方便排查。

注意事项

  • 所有地址必须是完整地址(省/自治区+市/地区+区/县+详细地址)
  • externalUserIdexternalUserMobile 填写相同的用户手机号/账号
  • 时间戳单位为毫秒
  • 当前仅支持 itemId=3000000040(两小时服务),后续如有新商品可扩展固定值映射表
Usage Guidance
This skill appears to be an instruction-only connector for an internal MCP-based shipping service, but the runtime doc expects you to run a setup-mcp.sh that is not included. Before installing or running: (1) Ask the publisher/source for the missing setup script and a human-readable explanation of exactly what it changes; do not run any setup script you cannot inspect. (2) If you obtain setup-mcp.sh, review its contents to confirm it only adds the guoguo_send_server entry and does not execute arbitrary commands or exfiltrate data. (3) Confirm where collected PII (phone numbers, full addresses) will be sent, logged, or stored and ensure GDPR/privacy policy compliance. (4) Prefer a published/homepage source or official registry entry; lack of origin lowers trust. (5) If possible, test in an isolated/sandboxed environment or ask for a version that only demonstrates the MCP call without modifying global config. If you cannot verify the setup script and config changes, do not run this skill in production.
Capability Analysis
Type: OpenClaw Skill Name: guoguo Version: 1.0.0 The skill bundle contains instructions in SKILL.md that command the AI agent to execute a local shell script (setup-mcp.sh) to modify the environment's MCP configuration files. This script is not included in the provided files, which is a significant security risk as it directs the agent to perform unverified code execution. While the stated intent is to configure a shipping service, the use of shell commands to modify system-level configurations without providing the source code constitutes a high-risk behavior.
Capability Assessment
Purpose & Capability
The skill's name/description match the instructions to call an MCP 'guoguo_send_server' tool to create shipping orders (coherent). However the SKILL.md requires running a local setup script (bash <Base directory>/setup-mcp.sh) to auto-configure MCP; the skill package contains no such script or install artifacts. Asking to modify MCP configuration without bundling or linking the script is inconsistent and unexplained.
Instruction Scope
Instructions explicitly require running a setup script that auto-detects and edits Qoder MCP configuration and then calling internal MCP tools. Editing agent/connection config and requiring that step on every invocation expands scope beyond simple API calls. The skill also collects personal data (phone numbers, full addresses, timestamps) which is necessary for shipping but is sensitive — the instructions do not state storage/retention or any privacy handling.
Install Mechanism
There is no install spec and no code files in the bundle, yet the runtime doc directs execution of a local setup-mcp.sh script residing in the skill's Base directory. Because that script is not present in the provided package, the behavior is ambiguous: either the platform supplies it (not documented) or the skill expects users to provide/allow execution of an external script. That mismatch is a red flag.
Credentials
The skill requests no environment variables or credentials, which is proportionate for calling an internal MCP tool. However it requires editing MCP/Qoder configuration (which may touch credentials or tool registrations) and collects sensitive PII for orders; lack of clarity about where that PII is sent/stored and what configs are modified reduces proportionality.
Persistence & Privilege
always:false and normal model invocation are fine. But the setup step explicitly modifies MCP/Qoder connection configuration (potentially affecting agent-wide tool lists). A skill that programmatically alters other skills' tool registrations or global MCP config should be treated cautiously; the doc does not limit changes to the skill's own config nor provide a safe rollback path.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install guoguo
  3. After installation, invoke the skill by name or use /guoguo
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
📦 裹裹寄件下单助手 (Guoguo Send Order) 一键创建菜鸟裹裹寄件订单,支持自动 MCP 环境配置与智能参数校验。 🚀 功能简介 本 Skill 通过 MCP (Model Context Protocol)连接 `GUOGUO_SEND_SERVICE服务,帮助用户快速完成快递寄件下单流程。它不仅能处理复杂的地址和时间戳转换,还内置了自动环境检测与配置脚本,确保在无预配置环境下也能无缝运行。 ✨ 核心特性 🔌 自动 MCP 配置:首次使用时自动检测并执行 setup-mcp.sh 脚本,兼容 macOS/Linux,自动注入 guoguo_send_server 配置。 📝智能参数构造:自动将人类可读时间转换为毫秒级时间戳,并根据服务类型(itemId: 3000000040)自动计算2小时揽收窗口。 ✅ 完整地址校验:强制要求省市区+详细地址的完整格式,减少下单失败率。 📊 结构化反馈:清晰展示订单号、取件码及账号ID,或提供明确的失败原因排查建议。 🛠️ 使用场景 当用户表达以下意图时触发: “我要寄快递” “帮我下个裹裹订单” “创建寄件单” “预约上门取件” 📋必要信息收集 在执行下单前,Agent 需向用户确认以下信息: 下单账号:手机号(同时作为 externalUserId 和 externalUserMobile) 寄件人信息:姓名、电话、完整地址(例:西藏自治区阿里地区札达县托林镇丁丁卡牧场) 收件人信息:姓名、电话、完整地址(例:浙江省杭州市余杭区文一西路969号) 期望揽收时间:必须晚于当前时间(例:2026-04-18 14:00) ⚙️ 技术实现细节 MCP Tool: mcp_guoguo_send_server_GUOGUO_SEND_ORDER_CREATE 服务类型: 默认使用 itemId 3000000040 (两小时极速服务) 时间逻辑: appointGotStartTime: 用户指定时间转毫秒时间戳 appointGotEndTime: startTime + 7200000ms (固定2小时间隔) 前置检查: bash # 若未检测到 guoguo_send_server,自动执行: bash <Base directory>/setup-mcp.sh 📤输出示例 成功响应: ✅ 下单成功! 寄件单号: 21240720002375404 取件码: 5617 账号ID: 2074370454 失败响应: ❌ 下单失败:[具体错误原因,如地址解析失败/时间不可用等]
Metadata
Slug guoguo
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is guoguo?

裹裹寄件下单,通过MCP连接裹裹寄件服务创建寄件订单。当用户需要寄件、下单、创建寄件订单、寄快递时使用此skill。触发词:寄件、下单、寄快递、寄件下单、创建订单、裹裹下单。 It is an AI Agent Skill for Claude Code / OpenClaw, with 99 downloads so far.

How do I install guoguo?

Run "/install guoguo" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is guoguo free?

Yes, guoguo is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does guoguo support?

guoguo is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created guoguo?

It is built and maintained by dazhanggui (@dazhanggui); the current version is v1.0.0.

💬 Comments