mcdonalds-skill

Use when the user wants to connect to, test, or use the McDonalds service at mcp.mcd.cn, including checking authentication, probing MCP endpoints, listing tools, or calling McDonalds MCP tools through a reusable local CLI.

3,891 stars

Best use case

mcdonalds-skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Use when the user wants to connect to, test, or use the McDonalds service at mcp.mcd.cn, including checking authentication, probing MCP endpoints, listing tools, or calling McDonalds MCP tools through a reusable local CLI.

Teams using mcdonalds-skill should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/mcdonalds-skill/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/1052666/mcdonalds-skill/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/mcdonalds-skill/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How mcdonalds-skill Compares

Feature / Agentmcdonalds-skillStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Use when the user wants to connect to, test, or use the McDonalds service at mcp.mcd.cn, including checking authentication, probing MCP endpoints, listing tools, or calling McDonalds MCP tools through a reusable local CLI.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# 麦当劳 技能

## 适用场景
当用户想把麦当劳 MCP 接入为可复用能力,或需要检查 `https://mcp.mcd.cn` 这个远程 MCP 服务是否可连通、鉴权是否有效、是否能正常初始化、列出工具、以及执行具体工具调用时使用。

## 能力概览
这个技能提供了一个本地 CLI(`scripts/mcd_cli.py`),支持:
- 初始化并测试 MCP 握手
- 列出所有可用工具(含中文描述和参数定义)
- 调用任意工具并传入 JSON 参数
- 一键运行 smoke test(初始化 → 列出工具 → 真实调用)
- 将测试结果输出为 JSON 文件,便于复查
- 自动修复中文乱码(mojibake),Windows 下强制 UTF-8 输出

## 目录结构
- `SKILL.md`:技能说明
- `scripts/mcd_cli.py`:命令行工具(纯标准库,无第三方依赖)

## 服务信息
- 服务名:`mcdonalds`
- 类型:HTTP MCP(JSON-RPC 2.0)
- URL:`https://mcp.mcd.cn`
- 协议版本:`2024-11-05`
- 鉴权:`Authorization: Bearer <your-token>`

## 获取凭据
请让用户在此网址获取凭据:https://open.mcd.cn/mcp

获取后推荐配置为环境变量:
```bash
# Windows
set MCDONALDS_MCP_TOKEN=<your-token>

# Linux / macOS
export MCDONALDS_MCP_TOKEN=<your-token>
```

可选:`MCDONALDS_MCP_URL`(默认 `https://mcp.mcd.cn`)

也支持命令行通过 `--token` 显式传入。

## 常用命令
在 `skills/mcdonalds-skill/` 下执行:

```bash
# 初始化握手
python scripts/mcd_cli.py init --token <your-token>

# 列出所有工具(摘要模式)
python scripts/mcd_cli.py list-tools --token <your-token>

# 列出所有工具(完整原始 JSON)
python scripts/mcd_cli.py list-tools --token <your-token> --raw

# 调用工具(无参数)
python scripts/mcd_cli.py call --token <your-token> --tool now-time-info

# 调用工具(带 JSON 参数)
python scripts/mcd_cli.py call --token <your-token> --tool query-nearby-stores --args "{\"searchType\":2,\"beType\":1,\"city\":\"上海市\",\"keyword\":\"人民广场\"}"

# 一键 smoke test
python scripts/mcd_cli.py smoke-test --token <your-token>

# smoke test 并保存结果到文件
python scripts/mcd_cli.py smoke-test --token <your-token> --out report.json
```

如果已经设置环境变量,则可以省略 `--token`:
```bash
python scripts/mcd_cli.py smoke-test
```

## 命令说明

### 1. init
发送标准 `initialize` 请求,验证:
- URL 是否可达
- 凭据是否有效
- MCP 初始化是否成功

可选参数:`--no-raw-text` 不输出原始响应文本。

### 2. list-tools
调用 `tools/list`,返回可用工具列表。
默认会做适度摘要(工具名 + 描述 + inputSchema),避免终端刷屏;如需完整原始结果可加 `--raw`。

可选参数:`--no-raw-text` 不输出原始响应文本。

### 3. call
调用任意工具:
- `--tool <工具名>` 必填
- `--args '<json对象>'` 可选,默认 `{}`
- `--no-raw-text` 可选,不输出原始响应文本

### 4. smoke-test
自动执行完整链路测试:
1. `initialize` — 握手
2. `tools/list` — 获取工具列表
3. 选择一个默认测试工具(优先 `now-time-info` → `campaign-calendar` → `available-coupons`)做真实调用
4. 输出汇总 JSON 报告

可选参数:`--out <文件路径>` 将报告写入 JSON 文件。

## 可用工具列表(共 19 个)

| 工具名 | 说明 |
|--------|------|
| `now-time-info` | 获取当前服务器时间信息 |
| `campaign-calendar` | 查询当月营销活动日历 |
| `available-coupons` | 查询可领取的优惠券列表 |
| `auto-bind-coupons` | 一键领取所有可用优惠券 |
| `query-my-coupons` | 查看用户卡包中已有的券 |
| `query-store-coupons` | 查询当前门店可用的优惠券 |
| `query-my-account` | 查询用户积分账户详情 |
| `query-nearby-stores` | 到店场景下搜索附近门店 |
| `query-meals` | 查询门店餐品列表(到店/外送) |
| `query-meal-detail` | 查询餐品详情(到店/外送) |
| `calculate-price` | 计算商品价格(含优惠) |
| `create-order` | 创建麦当劳订单(到店/外送) |
| `query-order` | 查询订单详情和配送状态 |
| `delivery-query-addresses` | 查询用户配送地址列表 |
| `delivery-create-address` | 创建用户配送地址 |
| `mall-points-products` | 查询积分可兑换的商品列表 |
| `mall-product-detail` | 查询积分兑换商品详情 |
| `mall-create-order` | 创建积分兑换订单 |
| `list-nutrition-foods` | 获取餐品营养成分数据 |

## 常见判断
- 返回 `200` 且有 JSON-RPC `result`:服务正常可用
- 返回 `401/403`:凭据无效或无权限
- 返回 JSON-RPC `error`:服务可达,但请求参数或方法不对
- 返回 exit code `0`:命令成功;`1`:服务端返回异常;`2`:本地参数错误

## 常见报错排查

### 凭据缺失
请传 `--token`,或者设置环境变量 `MCDONALDS_MCP_TOKEN`。

### JSON 参数格式错误
`--args` 必须是合法 JSON 对象,例如:
```bash
--args "{}"
--args "{\"keyword\":\"鸡腿堡\"}"
```

### 工具调用失败
先运行:
```bash
python scripts/mcd_cli.py list-tools
```
确认工具名存在,再检查该工具所需参数(查看 `inputSchema`)。

## 设计原则
- 不把凭据写死到技能文件或脚本中,全部从环境变量或命令行参数读取
- 默认输出真实 MCP 返回的 JSON,避免"口头成功"
- 自动检测并修复中文 mojibake(服务器编码与终端编码不一致时)
- Windows 下强制 UTF-8 输出,避免 cp936 编码导致中文乱码
- 纯标准库实现,无需安装第三方依赖

Related Skills

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation