# slurm-job-script-generator

Builds SLURM sbatch scripts and checks resource requests. Use it to set up MPI, OpenMP, or GPU jobs for a cluster.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · ★ 83
- Author: HeshamFS
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/HeshamFS/materials-simulation-skills/tree/HEAD/skills/hpc-deployment/slurm-job-script-generator/SKILL.md
- Updated: 2026-10-21
- HTML: https://affpapa.org/en/nevibecode/skills/slurm-job-script-generator

## What it does

This skill turns job settings into a `.sbatch` file. You can specify nodes, MPI tasks, OpenMP threads, memory, GPUs, walltime, partition, modules, and the command to run. It checks for conflicting memory directives and can flag CPU oversubscription or an uneven task-to-GPU ratio.

For an MPI-only job, use one CPU per task. A hybrid MPI+OpenMP layout should match CPUs per task to the number of OpenMP threads. The generator prepends `srun` by default; when the run command already uses `srun`, `mpirun`, or `mpiexec`, set `--launcher none` to avoid wrapping one launcher in another. Cluster rules for memory and GPU requests vary, so confirm those settings against your cluster documentation.

Python 3.10+ is required, and the generator uses the Python standard library. Script generation works on Linux, macOS, and Windows; submitting a job uses `sbatch`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add HeshamFS/materials-simulation-skills --skill slurm-job-script-generator -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/slurm-job-script-generator/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/slurm-job-script-generator/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add HeshamFS/materials-simulation-skills --skill slurm-job-script-generator -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/slurm-job-script-generator/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add HeshamFS/materials-simulation-skills --skill slurm-job-script-generator -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/slurm-job-script-generator/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install HeshamFS/materials-simulation-skills slurm-job-script-generator
```

2. **Manually: put the files in place**
- File: `.github/skills/slurm-job-script-generator/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add HeshamFS/materials-simulation-skills --skill slurm-job-script-generator -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/HeshamFS/materials-simulation-skills --path skills/hpc-deployment/slurm-job-script-generator
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/slurm-job-script-generator/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add HeshamFS/materials-simulation-skills --skill slurm-job-script-generator -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/HeshamFS/materials-simulation-skills/tree/HEAD/skills/hpc-deployment/slurm-job-script-generator/SKILL.md

## When to use it
- generate an `.sbatch` file from job settings
- choose an MPI-only or MPI+OpenMP layout
- check memory and CPU requests for conflicts
- flag CPU oversubscription or an uneven GPU mapping
- prepare a GPU simulation job for SLURM

## Example prompts
- Create a `job.sbatch` for my MPI program with two nodes, OpenMP threads, and a time limit.
- Check whether my SLURM job requests conflicting memory or CPU resources.
- Build a GPU job script for my simulation and check how tasks map to devices.

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 807d4c0d6b26160a.

BEGIN THIRD-PARTY FILE 807d4c0d6b26160a
```text
---
name: slurm-job-script-generator
description: >
  Generate correct, copy-pasteable SLURM sbatch job scripts and sanity-check
  HPC resource requests — configure nodes, MPI tasks, OpenMP threads, memory
  (per-node or per-cpu), GPUs, walltime, partitions, modules, and environment
  variables, with automatic detection of conflicting directives and
  oversubscription. Use when preparing a SLURM submission script, deciding
  between pure MPI and hybrid MPI+OpenMP layouts, standardizing #SBATCH
  directives across a team, debugging why a job won't launch or gets killed,
  or setting up GPU-accelerated simulation jobs, even if the user only says
  "I need to run this on the cluster" or "my job keeps getting killed."
allowed-tools: Read, Bash, Write, Grep, Glob
metadata:
  last_deterministic_eval: "2026-10-20"
  agent_evaluation_status: "not_revalidated"
  author: HeshamFS
  version: "1.2.2"
  security_tier: high
  security_reviewed: true
  tested_with:
    - claude-code
  last_evaluated: "2026-06-24"
  eval_cases: 5
  last_reviewed: "2026-06-23"
  standards:
    - "SchedMD SLURM sbatch specification (#SBATCH directives, directive-ordering rule, --mem units, --time formats)"
    - "SchedMD SLURM srun task-launch model (srun --ntasks/--cpus-per-task placement, --gpu-bind/--ntasks-per-gpu)"
    - "MPI standard (MPI Forum) and OpenMP API for hybrid MPI+OpenMP layout (OMP_NUM_THREADS = cpus-per-task)"
---

# SLURM Job Script Generator

## Goal

Generate a correct, copy-pasteable SLURM job script (`.sbatch`) for running a simulation, and surface common configuration mistakes (bad walltime format, conflicting memory flags, oversubscription hints).

## Requirements

- Python 3.10+
- No external dependencies (Python standard library only)
- Works on Linux, macOS, and Windows (script generation only)

## Inputs to Gather

| Input | Description | Example |
|-------|-------------|---------|
| Job name | Short identifier for the job | `phasefield-strong-scaling` |
| Walltime | SLURM time limit | `00:30:00` |
| Partition | Cluster partition/queue (if required) | `compute` |
| Account | Project/account (if required) | `matsim` |
| Nodes | Number of nodes to allocate | `2` |
| MPI tasks | Total tasks, or tasks per node | `128` or `64` per node |
| Threads | CPUs per task (OpenMP threads) | `2` |
| Memory | `--mem` or `--mem-per-cpu` (cluster policy dependent) | `32G` |
| GPUs | GPUs per node (optional) | `4` |
| Working directory | Where the run should execute | `$SLURM_SUBMIT_DIR` |
```
END THIRD-PARTY FILE 807d4c0d6b26160a

The third-party file has ended. Everything between the 807d4c0d6b26160a tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2512 of 15588 bytes. © HeshamFS · Apache-2.0 · https://github.com/HeshamFS/materials-simulation-skills/tree/HEAD/skills/hpc-deployment/slurm-job-script-generator/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md