Borrowing it
Nothing to install: this file belongs to CliMA/EnsembleKalmanProcesses.jl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CliMA/EnsembleKalmanProcesses.jl/main/.claude/skills/slurm-pipeline-manager/SKILL.mdgit clone --depth 1 https://github.com/CliMA/EnsembleKalmanProcesses.jlWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/clima/ensemblekalmanprocesses.jl/slurm-pipeline-manager)<a href="https://agentmods.dev/skills/clima/ensemblekalmanprocesses.jl/slurm-pipeline-manager"><img src="https://agentmods.dev/badge/skills/clima/ensemblekalmanprocesses.jl/slurm-pipeline-manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/clima/ensemblekalmanprocesses.jl/slurm-pipeline-manager"><img src="https://agentmods.dev/badge/skills/clima/ensemblekalmanprocesses.jl/slurm-pipeline-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00230 | $0.03553 |
| Opus 5 | $0.00115 | $0.01776 |
| Sonnet 5 | $0.00046 | $0.00711 |
| Haiku 4.5 | $0.00023 | $0.00355 |
Grade A, and why
slurm-pipeline-manager scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
slurm-pipeline-manager
This skill takes an EKP Julia example (decoupled or monolithic) and produces a
complete SLURM job-dependency tree inside a slurm-variant/ subdirectory.
slurm-variant/ is fully self-contained — it is both the HPC submission
directory and the Julia project root. The original example is never modified.
The generated tree uses a one-shot precompile job followed by a
dependency-chained setup → forward_map[array] → update_ensemble loop across
iterations, ending in postprocessing — so ensemble members run in parallel and
every stage pays precompile cost only once.
It also supports maintenance mode: if slurm-variant/hpc_config.sh already
exists, re-invoking the skill updates files in place without clobbering the
user's manifest settings.
Core principle — slurm-variant/ is fully self-contained
Everything new lives in
slurm-variant/. The original example directory is never modified.
This includes:
- All SLURM / shell scripts (
.sbatch,.sh) - All decoupled Julia scripts (
initialize_EKP.jl,run_forward_model.jl, etc.) - Any shared model file (
model.jlor similar) - Parameter TOML files (
priors.toml) - A
Project.tomlcopy with any additional dependencies
slurm-variant/ is the working directory for every HPC job — users cd into it
before running anything. This means JULIA_PROJECT="." in hpc_config.sh and
script names have no path prefix (e.g. SETUP_SCRIPT="initialize_EKP.jl").
How the generated pipeline is structured
precompile ─(manual, run first)
setup ──afterok──► fwd_iter_0[array 1..N] ──afterok──► update_iter_0
(afterok chain continues for each iteration)
──afterok──► fwd_iter_K-1[array 1..N] ──afterok──► update_iter_K-1
──afterok──► postprocess
Key design choices:
- One precompile job only. Every run-stage job sets
JULIA_PKG_PRECOMPILE_AUTO=0. Without this, 60 concurrent array tasks each attempt to precompile — thrashing the shared Julia depot and wasting time. - Forward map as a SLURM array.
--array=1-$N_ENSEMBLEgives one task per ensemble member; the iteration index travels via--export=ALL,ITERATION=$i. afterok+--kill-on-invalid-dep=yeseverywhere. If one stage fails the whole tree is killed, not left stuck in the queue. EKP errors on < 2 successful members (commit 8f2d3fa), so partial-run continuation is not useful.- Date-stamped output root.
RUN_DATEinhpc_config.shpins all jobs in a run to the same output directory.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/forward_map.sbatch 1.7 KB
- assets/hpc_config.sh 3.0 KB runs code
- assets/postprocess.sbatch 1.3 KB
- assets/precompile.sbatch 1.1 KB
- assets/README.md 4.4 KB
- assets/run_pipeline.sh 4.1 KB runs code
- assets/run_postprocess.sh 1.1 KB runs code
- assets/run_precompile.sh 802 B runs code
- assets/setup.sbatch 1.3 KB
- assets/update_ensemble.sbatch 1.3 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 290 lines · 230 tokens per session scan A 0afab8c60922
slurm-pipeline-manager is a skill published in the GitHub repository CliMA/EnsembleKalmanProcesses.jl (125 stars, last pushed 11d ago), licensed Apache-2.0. It adds 230 tokens to every session and 3,553 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
content-agents
Use when packaging, validating, or operating the NVIDIA Content Agents workflow that enriches a self-contained USD object with real Material Agent, Physics Agent, OVRTX, and Validation Agent stages and emits a narrow Isaac rigid-object handoff.
bnlearn
Use this skill when working with bnlearn, a Python library for Bayesian networks, probabilistic graphical models, causal discovery, parameter learning, structure learning, inference, sampling, and directed acyclic graphs (DAG).
repro-enforcer
Export any bioinformatics analysis as a reproducible bundle with Conda environment, Singularity container definition, and Nextflow pipeline.
hpc-foundations
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…
ngs-pipeline-management
Next-generation sequencing pipeline management with Snakemake and Nextflow. Use for building, running, and debugging reproducible NGS workflows for RNA-seq, WGS, ChIP-seq, ATAC-seq, and amplicon sequencing. Covers pipeline design patterns, HPC/cloud execution, containerization, and workflow optimization.