executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
environment-and-model-setupSet up and verify Hunyuan3D-2 Python, CUDA, extension, and model-cache environments.
Independent GitHub snapshot · Automated classification · Original documentation governs
Use this sub-skill when the task is about installing hy3dgen, choosing PyTorch/CUDA variants, building texture extensions, validating GPU/backend readiness, selecting model subfolders, or planning local/offline model caches.
hy3dgen from a package source or a repository tree the user is intentionally working in.custom_rasterizer and mesh_processor for texture generation.HY3DGEN_MODELS cache behavior.../shape-generation/.../texture-and-mesh/.../services-and-integrations/.Examples:
python scripts/check_install.py --json
python scripts/check_install.py --check-cuda --json
python scripts/check_install.py --check-cuda --check-extensions --json
A passing helper check proves installation/backend readiness for the selected probes. It does not prove that full model inference ran or that model checkpoints are cached.