How do I install the Hpc Orchestration skill?

Run npx skillmds@latest add scimate-ai/hpc-orchestration in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Hpc Orchestration safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Hpc Orchestration?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Hpc Orchestration free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Hpc Orchestration?

scimate-ai (@scimate-ai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Hpc Orchestration by scimate-ai — Agent Skill

Name: Hpc Orchestration
Author: scimate-ai

Hpc Orchestration

Coordinate end-to-end HPC execution workflows across scheduler submission, job monitoring, log tracking, self-healing, and post-processing handoff. Use when a task spans Slurm, PBS, LSF, MPI sizing, queue operations, cluster-safe execution, or multi-stage HPC workflow orchestration.

scimate-ai f3fe5ab 31 files · 90.7 KB Updated Sep 17, 2026

File contents

HPC Orchestration

Use this skill as the repository-level execution layer above solver-specific HPC skills.

Start

Read references/cluster-operations-manual.md first for any end-to-end cluster workflow.
Read references/lifecycle-manual.md when coordinating solver skills with orchestration stages.
Read references/scheduler-and-parallelism.md when choosing scheduler directives or MPI sizing.
Read references/slurm-launch-patterns.md when the main decision is how to launch work inside a Slurm allocation.
Read references/environment-and-storage-hygiene.md when environment modules, scratch policy, or filesystem behavior may decide workflow reliability.
Read references/data-transfer-and-staging.md when files must be synchronized, staged, archived, or verified.
Read references/software-build-and-reproducibility.md when compilation, package stacks, or rebuildability are in scope.
Read references/interactive-debugging-and-profiling.md when the task needs live diagnosis, scaling studies, or profiler evidence.
Read references/remote-development-and-notebooks.md when VS Code Remote SSH, Jupyter, or port forwarding is involved.
Read references/container-workflows.md when Apptainer or Singularity-style execution is in scope.
Read references/public-protocol.md when aligning solver skills with the repository lifecycle contract.
Read references/error-pattern-dictionary.md when scheduler, monitoring, or log-tracking failures occur.

Additional References

Load these on demand:

references/tools-and-scripts.md for shared execution tool roles
references/ecosystem-roadmap.md for repository-wide coverage goals
references/legacy-template.md when adapting an older solver skill draft into the current format

Reusable Templates

Use assets/templates/ when a concrete scheduler scaffold is needed:

slurm-basic.sh
slurm-array.sh
slurm-packed-single-node.sh
slurm-apptainer.sh
slurm-perf-report.sh
pbs-basic.sh
lsf-basic.sh
rsync-stage-in.sh
jupyter-lab-compute.sh
ssh-config-compute-proxy.example

Shared Scripts

Use scripts/ for deterministic orchestration tasks:

hpc_job_submitter.py
hpc_job_monitor.py
hpc_log_tracker.py
hpc_slurm_deploy.py

Guardrails

Do not run heavy MPI workloads on login nodes.
Do not separate queue submission from runtime monitoring in a production workflow.
Do not resubmit unchanged failing jobs when a solver-specific error dictionary exists.
Do not choose core counts without a scale-based heuristic.

---name: hpc-orchestrationdescription: Coordinate end-to-end HPC execution workflows across scheduler submission, job monitoring, log tracking, self-healing, and post-processing handoff. Use when a task spans Slurm, PBS, LSF, MPI sizing, queue operations, cluster-safe execution, or multi-stage HPC workflow orchestration.---# HPC OrchestrationUse this skill as the repository-level execution layer above solver-specific HPC skills.## Start1. Read `references/cluster-operations-manual.md` first for any end-to-end cluster workflow.2. Read `references/lifecycle-manual.md` when coordinating solver skills with orchestration stages.3. Read `references/scheduler-and-parallelism.md` when choosing scheduler directives or MPI sizing.4. Read `references/slurm-launch-patterns.md` when the main decision is how to launch work inside a Slurm allocation.5. Read `references/environment-and-storage-hygiene.md` when environment modules, scratch policy, or filesystem behavior may decide workflow reliability.6. Read `references/data-transfer-and-staging.md` when files must be synchronized, staged, archived, or verified.7. Read `references/software-build-and-reproducibility.md` when compilation, package stacks, or rebuildability are in scope.8. Read `references/interactive-debugging-and-profiling.md` when the task needs live diagnosis, scaling studies, or profiler evidence.9. Read `references/remote-development-and-notebooks.md` when VS Code Remote SSH, Jupyter, or port forwarding is involved.10. Read `references/container-workflows.md` when Apptainer or Singularity-style execution is in scope.11. Read `references/public-protocol.md` when aligning solver skills with the repository lifecycle contract.12. Read `references/error-pattern-dictionary.md` when scheduler, monitoring, or log-tracking failures occur.## Additional ReferencesLoad these on demand:- `references/tools-and-scripts.md` for shared execution tool roles- `references/ecosystem-roadmap.md` for repository-wide coverage goals- `references/legacy-template.md` when adapting an older solver skill draft into the current format## Reusable TemplatesUse `assets/templates/` when a concrete scheduler scaffold is needed:- `slurm-basic.sh`- `slurm-array.sh`- `slurm-packed-single-node.sh`- `slurm-apptainer.sh`- `slurm-perf-report.sh`- `pbs-basic.sh`- `lsf-basic.sh`- `rsync-stage-in.sh`- `jupyter-lab-compute.sh`- `ssh-config-compute-proxy.example`## Shared ScriptsUse `scripts/` for deterministic orchestration tasks:- `hpc_job_submitter.py`- `hpc_job_monitor.py`- `hpc_log_tracker.py`- `hpc_slurm_deploy.py`## Guardrails- Do not run heavy MPI workloads on login nodes.- Do not separate queue submission from runtime monitoring in a production workflow.- Do not resubmit unchanged failing jobs when a solver-specific error dictionary exists.- Do not choose core counts without a scale-based heuristic.

Frequently asked questions