一键导入
scene
Entry point for static scene plans (plan_type=scene). Routes the agent to the correct scene, system, and camera skills and defines only high-level invariants.
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。
菜单
Entry point for static scene plans (plan_type=scene). Routes the agent to the correct scene, system, and camera skills and defines only high-level invariants.
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。
基于 SOC 职业分类
Entry point for FSI-coupled hybrid plans (plan_type=fsi_in_scene) — any scene combining SPH fluid (water tanks, dam-break, wave channels) with multi-body dynamics, optionally with a wheeled vehicle. Pick this over mbs_in_scene whenever the plan involves a fluid domain (scene_objects with domain_type starting "sph_") or an FSI body registration (scene_objects with fsi_registration set). Routes to fsi/sph (always), veh/wheeled_vehicle (when vehicle present), and enforces FSI-specific invariants distinct from generic mbs_in_scene rigid scenes.
Entry point for rigid-body hybrid plans (plan_type=mbs_in_scene) combining a robot or vehicle with scene assets — NO fluid coupling. Routes to the correct domain skills and defines only high-level invariants. Use core/fsi_in_scene instead when the plan involves SPH fluid or FSI body registration.
Entry point for pure multi-body simulation plans (plan_type=mbs). Routes the agent to the correct mechanics, system, and camera skills and defines only high-level invariants.
Set up SPH-based Fluid-Structure Interaction (FSI): create ChFsiFluidSystemSPH and ChFsiSystemSPH, configure fluid and SPH parameters, seed fluid particles with hydrostatic initialization, add container BCE boundary markers, register floating rigid bodies, optionally couple with a wheeled vehicle, and advance with sysFSI.DoStepDynamics(dT).
Translate a `geometry_relations` entry from the plan into correct PyChrono coordinate code. Read this whenever the plan declares a relation_name you have not previously encoded, and especially BEFORE writing SetPos / camera placement for any body that participates in a multi-body geometric constraint. Each subsection below is one canonical pattern named exactly as it appears in `plan.geometry_relations[i].relation_name`.
Create rigid bodies with mass, geometry, collision shapes, and visual assets.
| name | scene |
| description | Entry point for static scene plans (plan_type=scene). Routes the agent to the correct scene, system, and camera skills and defines only high-level invariants. |
| compatibility | pychrono >= 8.0 |
| metadata | {"domain":"core"} |
Use this skill when plan_type = "scene".
This core skill is a router and constraint layer, not a recipe catalog. It decides which child skills must be read and states scene-wide invariants that apply regardless of the specific asset family. Concrete asset-loading APIs, placement recipes, camera layouts, and scenario-specific code patterns belong to the owning child skills.
This core skill covers only:
This core skill does not define:
| Skill | Why it is required |
|---|---|
mbs/system_create | Choose and configure the physical system, gravity, solver |
vsg | VSG visualization window setup, camera, grid, sky, render loop |
sens/camera | Sensor manager, setup_preview_camera, recorder loop integration, camera output behavior |
After reading this core skill, read the child skill that actually owns the asset family:
scene/* skill for the asset family in the plan.chrono_code.utils / chrono_code.utils.scene_assets.If a child skill owns a utility or asset pipeline, that child skill is authoritative for the concrete API and code pattern.
| Skill | When to read |
|---|---|
mbs/body_creation | Manual body creation when not using a scene utility pipeline |
mbs/collision | Contact material choice and collision shapes |
planning/scene_coordinate_system | Scene predicate algebra and authored layout semantics |
planning/asset_discovery | Discovering available assets and paths |
Z-up unless a child skill explicitly owns a different convention.VSG window viewpoint and sensor cameras are separate concerns:
vis.AddCamera(...) sets the interactive VSG window viewsetup_preview_camera(...) creates actual sensor-camera outputchrono.SetChronoDataPath() by default. Trust the default data path unless an owning child skill explicitly says otherwise.vis.AddCamera(...) must be configured before vis.Initialize().scene family.scene/* child skill for the asset family in the plan.scene problem; route to core/mbs_in_scene.setup_preview_camera() from sens/camera; vis.AddCamera(...) alone is not enough.If you are writing or updating a core scene skill, do not place these here:
AssetDescriptor(...), create_asset_body(...), or add_visual_assets(...) recipesThose belong in the owning child skills.