This connects Claude to the Amap (高德地图) API for route planning and POI searches across China. It handles driving, walking, cycling, and transit directions between locations, plus searches for attractions and restaurants with decent filtering (景点 combines scenic spots and museums, 餐厅 excludes fast food). The CLI takes either place names or coordinates, and there's some nice flexibility with JSON output and city code lookups. You'll need your own Amap API key to make it work. Most useful if you're building travel planning features or location-based recommendations for Chinese cities, since it taps into one of the country's most comprehensive mapping services.

GitHub stars
722
last updated
Jun 1, 2026

Install

$ npx -y skills add countbot-ai/countbot --skill map --agent claude-code

Installs into .claude/skills of the current project.

Files

地图路线规划与 POI 搜索

基于高德地图 API 的路线规划和 POI 搜索服务。

配置

编辑 skills/map/scripts/config.json,填写高德地图 API Key:

{
  "amap_key": "YOUR_AMAP_KEY"
}

AI 调用示例

用户说"我想去东莞玩3天":

# 1. 搜索景点
python3 skills/map/scripts/map.py attractions --city 东莞 --page-size 20 --json

# 2. 查询景点间路线
python3 skills/map/scripts/map.py driving --origin "旗峰公园" --destination "可园博物馆" --origin-city 东莞 --dest-city 东莞

用户说"东莞有什么好吃的":

python3 skills/map/scripts/map.py restaurants --city 东莞 --page-size 20 --json

用户说"从天安门到鸟巢坐地铁怎么走":

python3 skills/map/scripts/map.py transit --origin "天安门" --destination "鸟巢" --city1 010 --city2 010

命令行参考

路线规划

# 驾车
python3 skills/map/scripts/map.py driving --origin "起点" --destination "终点" --origin-city 城市 --dest-city 城市

# 步行
python3 skills/map/scripts/map.py walking --origin "起点" --destination "终点" --origin-city 城市 --dest-city 城市

# 公交(需要城市编码)
python3 skills/map/scripts/map.py transit --origin "起点" --destination "终点" --city1 编码 --city2 编码

# 显示详细步骤
python3 skills/map/scripts/map.py driving --origin "起点" --destination "终点" --show-steps

POI 搜索

Sponsors

Details

Repository
github.com/countbot-ai/countbot
License
MIT
First seen
Jun 11, 2026

More from countbot-ai/countbot

All 14

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps 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 int4.3Mskills.sh installs