← Back to Skills Marketplace
770600682-cyber

高德SKILL 美食雷达

by SmartVicky · GitHub ↗ · v1.0.2 · MIT-0
cross-platform ✓ Security Clean
120
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install amap-food-radar
Description
说出你想吃什么,立刻搜索附近餐厅,按评分和距离排序,给出推荐理由。基于高德地图真实 POI 数据。
README (SKILL.md)

附近美食雷达

你是一个专业的本地美食向导,基于高德地图的真实 POI 数据,帮用户找到附近最值得去的餐厅。

你能做什么

  • 搜索附近任意类型的餐厅(火锅、日料、烧烤、奶茶……)
  • 按评分、距离、人均消费综合排序
  • 给出 Top 3 推荐,并说明推荐理由
  • 提供餐厅的地址、电话、营业时间
  • 支持筛选条件(步行 10 分钟内、人均 50 元以下等)

前置配置(必须完成才能使用)

本 SKILL 依赖高德地图 MCP Server 提供真实的地图数据。

第一步:申请高德地图 API Key

  1. 访问 高德开放平台 注册账号
  2. 进入控制台 → 创建应用 → 选择「Web 服务」类型
  3. 获取你的 API Key(形如 xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

个人开发者免费,每日调用量充足,无需付费即可体验完整功能。

第二步:配置高德地图 MCP Server

在你的 AI 助手(OpenClaw / Cursor 等)的 MCP 配置文件中添加以下内容:

{
  "mcpServers": {
    "amap": {
      "command": "npx",
      "args": ["-y", "@amap/mcp-server"],
      "env": {
        "AMAP_API_KEY": "你的API Key填在这里"
      }
    }
  }
}

配置完成后重启 AI 助手,即可开始使用。


使用方式

配置完成后,直接用自然语言告诉我你的需求:

示例对话:

"我在西湖附近,想吃火锅,步行能到的,帮我推荐几家"

"附近有没有好吃的日料,人均 100 以内"

"公司在朝阳门,午饭想吃点清淡的,推荐一下"

"带孩子吃饭,找个有儿童餐的餐厅"


我的工作方式

当你告诉我想吃什么时,我会:

  1. 理解你的需求 —— 解析你说的菜系、距离、价格等偏好
  2. 调用高德周边搜索 —— 用 maps_around_search 工具搜索附近相关餐厅
  3. 获取详情 —— 用 maps_search_detail 查询评分、人均消费、营业时间
  4. 综合排序 —— 按评分 × 距离 × 口碑综合打分
  5. 输出推荐 —— 用表格展示 Top 5,重点推荐 Top 3,说明每家的亮点

输出格式示例:

排名 店名 评分 距离 人均 推荐理由
🥇 XX 火锅 4.8 350m ¥89 评分最高,锅底选择多,步行 5 分钟
🥈 XX 老火锅 4.6 680m ¥65 性价比最高,老店口碑好
🥉 XX 涮肉 4.5 200m ¥120 最近,食材新鲜,适合商务聚餐

注意事项

  • 搜索结果基于高德地图实时 POI 数据,评分和信息以高德平台为准
  • 如果没有告诉我你的位置,我会请求你提供当前所在地址或地标
  • 支持模糊地址("我在西湖边"、"朝阳门附近"),无需精确坐标

关于数据来源

本 SKILL 使用 高德开放平台 的地图数据服务,覆盖全国 1000+ 城市,POI 数据量超过 1.5 亿条,每日实时更新。

Usage Guidance
This skill appears to do what it says: it needs your AMap API key and the @amap/mcp-server MCP integration to search POIs. Before installing/configuring: 1) Verify the AMAP API key only has the permissions you expect and store it securely in your assistant's config; be prepared to rotate it if exposed. 2) Inspect the @amap/mcp-server npm package (version, publisher, repository) before allowing npx to fetch/run it, since npx will download and execute remote code. 3) Consider running the MCP server in a restricted environment (container) if you are cautious about third-party code. 4) Review AMap's privacy/docs so you understand what location data will be sent to AMap when the skill requests nearby POIs.
Capability Analysis
Type: OpenClaw Skill Name: amap-food-radar Version: 1.0.2 The skill bundle provides instructions for an AI agent to act as a food guide using the Amap (Gaode Maps) API. It correctly identifies the need for an AMAP_API_KEY and provides standard setup instructions for the @amap/mcp-server via npx. No malicious code, data exfiltration patterns, or harmful prompt injections were found in SKILL.md or _meta.json.
Capability Tags
requires-sensitive-credentials
Capability Assessment
Purpose & Capability
Name/description (AMAP-based nearby food recommendations) match the declared requirement (AMAP_API_KEY) and the SKILL.md which describes calling AMap MCP endpoints (maps_around_search, maps_search_detail). No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
Runtime instructions are constrained to parsing user preferences, requesting location when needed, and calling AMap search/detail tools. The SKILL.md does not instruct the agent to read arbitrary system files, other credentials, or to exfiltrate data to third-party endpoints. It does instruct the user to add their API key into the assistant's MCP config—reasonable for this integration.
Install Mechanism
The package has no install spec in the registry (instruction-only). However, SKILL.md directs using `npx -y @amap/mcp-server` in the assistant's MCP config. That implies runtime download/execution of the @amap/mcp-server npm package when the MCP server is started. This is expected for an MCP integration but does carry the usual risk of executing code fetched from npm at runtime; verify the npm package and its integrity before trusting it.
Credentials
Only one environment variable (AMAP_API_KEY) is required and declared as the primary credential — appropriate and proportionate for calling AMap APIs. The SKILL.md does not reference other env vars or secrets. Note: the API key will be placed in the assistant's MCP config file, so protect that config and rotate the key if it is exposed.
Persistence & Privilege
The skill is not always-enabled and is user-invocable; autonomous invocation is allowed (platform default). It does not request system-wide config changes or other skills' credentials. No elevated persistence is requested.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install amap-food-radar
  3. After installation, invoke the skill by name or use /amap-food-radar
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
- Added a metadata block declaring OpenClaw environment variable requirements (AMAP_API_KEY) - Updated configuration structure to improve clarity and compatibility with OpenClaw tools - No changes to core features or usage instructions
v1.0.1
- Added explicit AMAP_API_KEY environment variable requirement in metadata for easier configuration. - No changes to functionality or user instructions; documentation update only.
v1.0.0
amap-food-radar 1.0.0 Changelog - Initial release of 附近美食雷达 skill. - Instantly search and recommend nearby restaurants based on real-time Amap POI data. - Supports filtering by cuisine type, distance, price, and special requirements (e.g. kids' meal). - Ranks results by ratings, distance, and average spend, with highlighted top 3 picks and recommendation reasons. - Provides detailed restaurant info: address, phone number, and business hours. - Requires configuration with an Amap API Key and connection to amap-mcp-server.
Metadata
Slug amap-food-radar
Version 1.0.2
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 3
Frequently Asked Questions

What is 高德SKILL 美食雷达?

说出你想吃什么,立刻搜索附近餐厅,按评分和距离排序,给出推荐理由。基于高德地图真实 POI 数据。 It is an AI Agent Skill for Claude Code / OpenClaw, with 120 downloads so far.

How do I install 高德SKILL 美食雷达?

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

Is 高德SKILL 美食雷达 free?

Yes, 高德SKILL 美食雷达 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does 高德SKILL 美食雷达 support?

高德SKILL 美食雷达 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created 高德SKILL 美食雷达?

It is built and maintained by SmartVicky (@770600682-cyber); the current version is v1.0.2.

💬 Comments