菜单
Build, review, debug, and stabilize Spack-based HPC software stacks. Use when working with Spack specs, variants, compilers, externals, environments, concretization, compiler or MPI matrices, site stacks, binary reuse, or Spack install and reuse failures.
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
Create, review, debug, and recover LS-DYNA keyword decks and simulation workflows. Use when working with LS-DYNA `*.k` or `*.key` input files, include trees, explicit crash or impact models, implicit static or quasi-static solves, contact definitions, section and material selection, timestep or mass-scaling control, hourglass stabilization, thermal or coupled workflows, ALE/SPH/ICFD/EM/DEM/CESE/IGA cases, or LS-DYNA runtime instability and model-quality issues.
Build, review, debug, and automate Gmsh geometry and meshing workflows. Use when working with `.geo` scripts, the Gmsh Python API, GEO versus OpenCASCADE modeling, physical groups, mesh-size fields, transfinite or recombine options, boundary layers, structured/unstructured algorithm selection, mesh partitioning, periodic meshes, high-order elements, mesh export and solver handoff (FEniCS, OpenFOAM, Elmer, SU2, etc.), CAD/STL import, or Gmsh CLI and meshing failures.
Generate, review, debug, and recover OpenFOAM case files for CFD workflows. Use when working with OpenFOAM dictionaries, case structure, turbulence fields, boundary conditions, decomposition, numerics, or OpenFOAM runtime errors. Also covers RANS/LES turbulence setup, wall functions, y+ targeting, conjugate heat transfer, compressible flows, VOF multiphase, mesh quality, and scheme tuning.
Build, review, debug, and automate VASP first-principles workflows. Use when working with VASP input sets such as INCAR, POSCAR, KPOINTS, and POTCAR; when choosing SCF, relaxation, static, DOS, or band-structure stages; or when fixing convergence, symmetry, cutoff, and k-point issues. Also covers magnetic calculations, spin-orbit coupling, hybrid functionals, surface slabs, DFT+U, van der Waals, phonons, molecular dynamics, NEB, and defect calculations.
Navigate foundational HPC knowledge across concepts, architectures, schedulers, Linux usage, storage and RDMA, containers, cloud basics, and cluster administration patterns distilled from hpclib.com. Use when the task is about understanding or explaining HPC basics, Slurm or PBS or LSF concepts, Linux-on-cluster workflows, software environment setup, storage or network fundamentals, or when turning general HPC knowledge into future skills.
Build, review, debug, and launch CUDA- and GPU-accelerated HPC workflows. Use when working with `nvcc`, host-compiler compatibility, CUDA-aware MPI, rank-to-GPU mapping, `CUDA_VISIBLE_DEVICES`, Slurm GPU scheduling, GPU memory or stream behavior, or CUDA build and runtime failures.
| name | hpc-spack |
| description | Build, review, debug, and stabilize Spack-based HPC software stacks. Use when working with Spack specs, variants, compilers, externals, environments, concretization, compiler or MPI matrices, site stacks, binary reuse, or Spack install and reuse failures. |
Treat Spack as a stack manager, not just an install command. Decide the compiler, MPI, externals, concretization policy, and environment boundary before changing package-level variants.
references/spec-and-variant-matrix.md before writing or repairing a Spack spec.references/compilers-and-external-packages.md when compiler registration, packages.yaml, or external software ownership is in scope.references/environments-and-concretization.md when using spack.yaml, lockfiles, unified concretization, or multi-package environments.references/compiler-and-mpi-matrix.md when the stack depends on compiler or MPI families and their combinations.references/modules-buildcaches-and-binary-reuse.md when integrating site modules, buildcaches, mirrors, or binary reuse.references/site-stack-and-reproducibility.md when the goal is a durable site stack, reproducible environment, or cluster handoff.references/error-recovery.md when concretization, install, compiler detection, external-package, or reuse behavior fails.Load these on demand:
references/spec-and-variant-matrix.md for spec syntax and variant selection patternsreferences/compilers-and-external-packages.md for compiler registration and external package ownershipreferences/environments-and-concretization.md for spack.yaml, lockfiles, and concretization behaviorreferences/compiler-and-mpi-matrix.md for compiler/MPI cross-product planningreferences/modules-buildcaches-and-binary-reuse.md for binary reuse and module integrationreferences/site-stack-and-reproducibility.md for site-stack hygiene and durable reproducibilityreferences/error-pattern-dictionary.md for fast matching of common Spack failure classesUse assets/templates/ when a concrete starting point is faster than rebuilding the Spack workflow from scratch, especially:
spack-env-minimal.yamlpackages-external-example.yamlcompilers-example.yamlspack-create-env-and-install.shspack-build-smoke-slurm.shSummarize: