Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

run-experiment

Estrelas2

Forks0

Atualizado10 de junho de 2026 às 00:37

Plans and launches an hmfast experiment (training, inference, or scan) on the cluster with safe resource limits. Use when the user wants to run something that costs nontrivial compute, especially on GPU.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

licongxu

licongxu/JXPaint

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Administradores de redes e sistemas de computadorInformática e Matemática·SOC 15-1244

SKILL.md

readonly

name	run-experiment
description	Plans and launches an hmfast experiment (training, inference, or scan) on the cluster with safe resource limits. Use when the user wants to run something that costs nontrivial compute, especially on GPU.

Run experiment

Follow .claude/rules/cluster-usage.md and, for autonomous sessions, .claude/rules/autonomous-operation.md.

Pre-flight

Identify the device. GPU partition? Which one? Quick nvidia-smi check on the target node.
Estimate memory. Sum array sizes in floats; multiply by 8 bytes (x64 default). Confirm it fits with headroom for JAX's default 75% preallocation. Show the arithmetic.
Estimate runtime. Run a tiny version (small N, few steps) and extrapolate. If the extrapolation is unclear, ask the user before launching the full run.
Pick a seed and config. Save both into the output directory.

Launch

Always via SLURM if estimated runtime > 10 min.
Job script must set --time, --mem, --gres=gpu:1 (when GPU is needed), and --output=logs/%x-%j.out.

Activate the env inside the job script:

source /scratch/scratch-lxu/venv/cmbagent_env/bin/activate

Outputs go under /scratch/scratch-lxu/... (working) or /rds/rds-lxu/... (persistent), never inside the repo.

During and after

Stream the log: tail -f logs/<jobname>-<jobid>.out.
On finish, verify saved arrays are finite and have the expected shapes.
Write a run.json manifest with: git hash, full config, seed, MaxRSS, wall time, output paths.

Stop conditions

If during the run you see OOM, repeated NaNs, or runtime exceeding the estimate by more than 2x, stop and report before resubmitting. Do not blindly retry with the same parameters.

Mais deste repositório

mesmo repositório

code-review

licongxu/JXPaint

Reviews proposed changes to hmfast for correctness, JAX compatibility, API layering, test coverage, and hardware-cost surprises. Use when the user asks for a review, a sanity check on a diff, or before merging a feature branch.

2026-06-102

cosmology-emulators

licongxu/JXPaint

Guides changes to hmfast Cosmology, emulator loading, and cosmological parameter sets. Use when editing cosmology.py, emulator_load.py, download.py, or adding new emulator_set keys.

2026-06-102

debug-hpc-job

licongxu/JXPaint

Diagnoses a failed or stuck SLURM/HPC job for hmfast (OOM, timeout, NaNs, CUDA errors, missing outputs). Use when the user asks "why did my job fail" or shows a SLURM log.

2026-06-102

halo-model-workflow

licongxu/JXPaint

Guides edits to hmfast's differentiable JAX halo model (HaloModel, mass function, bias, concentration, profiles). Use when changing src/hmfast/halos/, power-spectrum methods, or halo-model consistency flags.

2026-06-102

tracers-and-profiles

licongxu/JXPaint

Guides adding or modifying hmfast tracers and halo profiles. Use when editing src/hmfast/tracers/ or src/hmfast/halos/profiles/, or integrating new observables with HaloModel.

2026-06-102

write-paper-section

licongxu/JXPaint

Drafts or revises a section of an astrophysics or cosmology manuscript based on hmfast results. Use when the user asks for a draft, an edit pass, or a publishability review of a section, including its figures.

2026-06-102

name	run-experiment
description	Plans and launches an hmfast experiment (training, inference, or scan) on the cluster with safe resource limits. Use when the user wants to run something that costs nontrivial compute, especially on GPU.

Run experiment

Follow .claude/rules/cluster-usage.md and, for autonomous sessions, .claude/rules/autonomous-operation.md.

Pre-flight

Identify the device. GPU partition? Which one? Quick nvidia-smi check on the target node.
Estimate memory. Sum array sizes in floats; multiply by 8 bytes (x64 default). Confirm it fits with headroom for JAX's default 75% preallocation. Show the arithmetic.
Estimate runtime. Run a tiny version (small N, few steps) and extrapolate. If the extrapolation is unclear, ask the user before launching the full run.
Pick a seed and config. Save both into the output directory.

Launch

Always via SLURM if estimated runtime > 10 min.
Job script must set --time, --mem, --gres=gpu:1 (when GPU is needed), and --output=logs/%x-%j.out.

Activate the env inside the job script:

source /scratch/scratch-lxu/venv/cmbagent_env/bin/activate

Outputs go under /scratch/scratch-lxu/... (working) or /rds/rds-lxu/... (persistent), never inside the repo.

During and after

Stream the log: tail -f logs/<jobname>-<jobid>.out.
On finish, verify saved arrays are finite and have the expected shapes.
Write a run.json manifest with: git hash, full config, seed, MaxRSS, wall time, output paths.

Stop conditions

If during the run you see OOM, repeated NaNs, or runtime exceeding the estimate by more than 2x, stop and report before resubmitting. Do not blindly retry with the same parameters.