Skills Plugins MCP Prompt Model 博客 我的中心

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 Curated skill Quality Excellent · 78 v1.0.0

Get

https://deepseekmodel.com/api/download.php?id=googlecloudplatform-race-condition-agents-planner-skills-gis-spatial-engineering-skill-md&format=skill
Download .skill Standard format with system_prompt and model_config, ready for any agent framework
The actual content of the system_prompt field in the .skill file.
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.
Keywords that activate this skill. Click one to copy it.

This skill does not provide trigger words.

The downloaded .skill package contains the following fields.
Field Description
formatFormat tag (skill/v1)
skill_idUnique skill ID
nameSkill name
versionVersion
descriptionDescription
categoryCategories (array)
trigger_wordsTrigger words
tagsTags
sourceSource
source_urlSource URL (this page)
exported_atExported at (set per download)
system_promptSystem prompt body
model_configModel config: provider / model / temperature / max_tokens / top_p
examplesExamples
install_guideImport guide for Coze / Dify / Claude / custom frameworks
The same skill can be exported in different platform formats.
.skill Standard format with system_prompt and model_config, ready for any agent framework Download
.skillpro Enhanced format with scripts, tools, dependencies and hooks Download
.json Plain JSON export with system_prompt and model parameters only Download
Coze Markdown with frontmatter, for Coze platform import Download
Dify Dify DSL, import directly after creating an app Download

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

验证码 --

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。