菜单
Hardware spec collection and theoretical peak performance calculation for HPC environments. Prerequisite: skills/ssh-management for remote access.
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
Compute budget management with phase-based termination criteria. Use when checking budget, determining project phase, or making stop decisions.
ChangeLog.md format spec for VibeCodeHPC. Use when writing or validating ChangeLog entries with compile/job/test/sota fields.
Compiler warning triage for HPC parallelization. Use when deciding whether to proceed with job execution after compile warnings.
Context window usage monitoring and auto-compact recovery. Use when context is filling up or after auto-compact occurs. Optional for strong models.
CLI and dependency installation guidance. Use when setting up VibeCodeHPC on a new environment — local PC, supercomputer, container, etc.
Evolutionary flat-directory exploration strategy for HPC optimization. Use when designing directory hierarchies or planning multi-generation parallelization strategies.
| name | hardware-info |
| description | Hardware spec collection and theoretical peak performance calculation for HPC environments. Prerequisite: skills/ssh-management for remote access. |
FLOPS = cores × freq(GHz) × 2(FMA) × SIMD_width
SIMD: SSE=2, AVX/AVX2=4, AVX-512=8 (FP64)
FLOPS = SMs × FP64_cores_per_SM × freq × 2(FMA)
Multi-GPU: multiply by GPU count
BW = channels × bus_width(bit)/8 × freq(MT/s)
hardware_info.md at project start with actual commands on compute nodesDetails:
references/collection_commands.md,references/hardware_info_template.md