From conserve
Establishes CPU/GPU baselines before resource-intensive operations like builds, training, or tests. Guides scoping, instrumentation, throttling, and logging for regression detection.
How this skill is triggered — by the user, by Claude, or both
Slash command
/conserve:cpu-gpu-performanceThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- [When to Use](#when-to-use)
token-conservation).cpu-gpu-performance:baselinecpu-gpu-performance:scopecpu-gpu-performance:instrumentcpu-gpu-performance:throttlecpu-gpu-performance:logCapture current utilization:
uptimeps -eo pcpu,cmd | headnvidia-smi --query-gpu=utilization.gpu,memory.used --format=csvNote which hosts/GPUs are already busy.
Record any CI/cluster budgets (time quotas, GPU hours) before launching work.
Set a per-task CPU minute / GPU minute budget that respects those limits.
pytest -kcargo test <module>perfintel vtunecargo flamegraphnvidia-smi dmonnsysnvprofnice, ionice, or Kubernetes/Slurm quotas to prevent starvation of shared nodes.Conclude by documenting the commands that were run and their resource cost (duration, CPU%, GPU%), confirming whether they remained within the per-task budget. If a full suite or long training run was necessary, justify why selective or staged approaches were not feasible. Capture any follow-up tasks, such as adding a new test marker or profiling documentation, to simplify future sessions.
pytest tests/test_orders.py -k test_refund instead of pytest -m slow"nvidia-smi dmon output to prove GPU idle time before scaling"Command not found Ensure all dependencies are installed and in PATH
Permission errors Check file permissions and run with appropriate privileges
Unexpected behavior
Enable verbose logging with --verbose flag
npx claudepluginhub athola/claude-night-market --plugin conserveDetects CPU, GPU, memory, and disk resources, then recommends parallel processing, GPU acceleration, or out-of-core strategies for scientific computing tasks.
Tracks CPU, memory, disk I/O, and network usage with top, ps, vmstat, iostat to identify bottlenecks and optimize resource allocation/costs.