gis-spatial-engineering
Use when the marathon plan needs a 26.2-mile physical route generated from road-network GeoJSON, or when the request mentions traffic impact, route variety via seed, finishing landmarks, or the zone-sweep algorithm. Triggered by route-planning or traffic-analysis language.
DeepseekModel
官方收录技能
质量 优秀 · 78
v1.0.0
获取
https://deepseekmodel.com/api/download.php?id=googlecloudplatform-race-condition-agents-planner-skills-gis-spatial-engineering-skill-md&format=skill
下载 .skill
标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name gis-spatial-engineering description Use when the marathon plan needs a 26.2-mile physical route generated from road-network GeoJSON, or when the request mentions traffic impact, route variety via seed, finishing landmarks, or the zone-sweep algorithm. Triggered by route-planning or traffic-analysis language. license Apache-2.0 metadata {"adk_additional_tools":["plan_marathon_route","report_marathon_route","assess_traffic_impact"]} GIS Spatial Engineering You use this skill to generate the physical path of the marathon. Geographic Context (Built-in Data) You have access to a road network GeoJSON located at assets/network.json . Key features available in this network include: Landmarks : Point features with properties.name (e.g., Mandalay Bay, Bellagio, Sphere, Las Vegas Sign, Allegiant Stadium, The Venetian, Michelob Ultra Arena, etc.). These landmarks are used automatically by plan_marathon_route() to build the route. Named Roads : All 34 LineString features have properties.name (e.g., Las Vegas Boulevard, Las Vegas Freeway, Sahara Avenue, Flamingo Road, Rainbow Boulevard, Paradise Road, Sunset Road, Tropicana Avenue, Desert Inn Road, Eastern Avenue, Maryland Parkway, etc.). Algorithm The default algorithm is zone-sweep : the route starts at the Las Vegas Sign, goes northbound on the Strip past MGM Grand, sweeps through city zones (neighborhoods) using non-crossing geometry, and finishes near a prominent landmark (e.g., Michelob Ultra Arena). The algorithm handles all route geometry automatically — you do not need to select petals or manually sequence landmarks. Instructions Just call it : plan_marathon_route() with no arguments produces a valid 26.2-mile zone-sweep route. Use finish_landmark and seed for variety. Precision : The tool uses interpolation to guarantee exactly 26.2 miles. GeoJSON : Input must be valid road network GeoJSON. Tools plan_marathon_route(finish_landmark: Optional[str] = None, seed: Optional[int] = None, geojson_data: Optional[str] = None) : Generate the exact 26.2-mile path. finish_landmark : Name of a landmark to finish near (e.g., "Michelob Ultra Arena" ). seed : Integer seed for route variety. Different seeds produce different routes. report_marathon_route(route_geojson: dict) : Emit the final GeoJSON to the system registry. Decision-Making Guidance For most requests, call plan_marathon_route() with default arguments. Use seed to generate alternative routes when the user wants variety. Use finish_landmark when the user specifies a preferred finishing area.
Agent 识别该技能的关键词,点击任意一个即可复制。
该技能未提供触发词。
下载的 .skill 包内含以下字段。
| 字段 | 说明 |
|---|---|
| format | 格式标识(skill/v1) |
| skill_id | 技能唯一 ID |
| name | 技能名称 |
| version | 版本号 |
| description | 技能描述 |
| category | 所属分类(数组) |
| trigger_words | 触发词列表 |
| tags | 标签列表 |
| source | 来源标识 |
| source_url | 来源链接(本页地址) |
| exported_at | 导出时间(每次下载生成) |
| system_prompt | 系统提示词正文 |
| model_config | 模型参数:provider / model / temperature / max_tokens / top_p |
| examples | 示例 |
| install_guide | 各平台导入说明(Coze / Dify / Claude / 自定义框架) |