用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/duclm1x1/Dive-Ai --skill wheels-router命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | wheels-router |
| description | Plan public transit trips globally using Wheels Router (Hong Kong) and Transitous (worldwide) |
| license | MIT |
| compatibility | opencode |
| metadata | {"transport":"mcp","coverage":"global","specialty":"hong-kong"} |
I help you plan public transit trips anywhere in the world by connecting to the Wheels Router MCP server.
For Hong Kong trips, I use the Wheels Router API which provides:
For worldwide trips, I use the Transitous API which covers:
Use this skill whenever you need to:
Examples:
Follow your mcporter skill, if you don't have one follow below:
Add to config/mcporter.json:
{
"mcpServers": {
"wheels-router": {
"description": "Plan public transit trips globally",
"baseUrl": "https://mcp.justusewheels.com/mcp"
}
}
}
Then call tools directly:
npx mcporter call wheels-router.search_location query="Hong Kong Airport"
npx mcporter call wheels-router.plan_trip origin="22.28,114.24" destination="22.31,113.92"
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"wheels-router": {
"command": "npx",
"args": ["mcp-remote", "https://mcp.justusewheels.com/mcp"]
}
}
}
Cursor/Windsurf/VS Code (.cursor/mcp.json or similar):
{
"mcpServers": {
"wheels-router": {
"command": "npx",
"args": ["mcp-remote", "https://mcp.justusewheels.com/mcp"]
}
}
}
search_locationSearch for places before planning trips. Always use this first if you don't have exact coordinates.
Parameters:
query (required): Place name or address (e.g., "Hong Kong Airport", "Yau Tong MTR Exit A2")limit (optional): Number of results (1-10, default 5)Example:
search_location({
query: "Hong Kong International Airport",
limit: 3
})
Returns:
display_name: Full addresslat, lon: Coordinates for use in plan_triptype, class: Location categoryplan_tripPlan a transit route between two points.
Parameters:
origin (required): Starting point as "lat,lon" or "stop:ID"destination (required): Ending point as "lat,lon" or "stop:ID"depart_at (optional): ISO 8601 departure time (e.g., "2026-01-26T10:00:00+08:00")arrive_by (optional): ISO 8601 arrival deadlinemodes (optional): Comma-separated modes like "mtr,bus,ferry" (only specify if needed)max_results (optional): Limit number of route options (1-5)Example:
plan_trip({
origin: "22.2836,114.2358",
destination: "22.3080,113.9185",
depart_at: "2026-01-26T14:30:00+08:00",
max_results: 3
})
Returns:
plans: Array of route options
duration_seconds: Total trip timefares_min, fares_max: Fare range in HKD (Hong Kong only)legs: Step-by-step directions
type: "walk", "transit", "wait", "station_transfer"search_location to find coordinates before calling plan_triplat,lon format for best resultsdepart_at or arrive_by for accurate schedulesmax_resultsfares_min and fares_max show the range—interchange discounts are noted separately when available// 1. Search for locations
const origins = await search_location({
query: "Yau Tong MTR Station",
limit: 1
});
const destinations = await search_location({
query: "Hong Kong Airport",
limit: 1
});
// 2. Plan the trip
const routes = await plan_trip({
origin: `${origins[0].lat},${origins[0].lon}`,
destination: `${destinations[0].lat},${destinations[0].lon}`,
depart_at: "2026-01-26T15:00:00+08:00",
max_results: 2
});
// 3. Present the best options to the user or present specific results but only if user asked specifically. By default just give them something like "[walk] > [3D] > [walk] > [Kwun Tong Line] > [walk]"- unless they ask for specifics.