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.
- License 许可
- MIT
- 最近更新
- 2026-11-09
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- hpc-orchestration
- risk
- low
- domain
- high-performance-computing
- source
- { "commit": "4ea8069188", "license": "MIT", "repository": "SciMate-AI/HPC-Skills", "imported_at": "2026-09-20" }
- license
- MIT
- version
- 1.0.0
- category
- high-performance-computing
- platforms
- [ "claude-code", "cursor", "codex", "gemini", "antigravity", "copilot" ]
- subdomain
- general
- description
- 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.
02 资源文件 25
- 脚本assets/templates/jupyter-lab-compute.sh282 B
- 脚本assets/templates/lsf-basic.sh186 B
- 脚本assets/templates/pbs-basic.sh233 B
- 脚本assets/templates/rsync-stage-in.sh160 B
- 脚本assets/templates/slurm-apptainer.sh614 B
- 脚本assets/templates/slurm-array.sh454 B
- 脚本assets/templates/slurm-basic.sh265 B
- 脚本assets/templates/slurm-packed-single-node.sh717 B
- 脚本assets/templates/slurm-perf-report.sh412 B
- 资产文件assets/templates/ssh-config-compute-proxy.example147 B
- 参考文档references/cluster-operations-manual.md7.6 KB
- 参考文档references/container-workflows.md4.6 KB
- 参考文档references/data-transfer-and-staging.md3.8 KB
- 参考文档references/ecosystem-roadmap.md8.2 KB
- 参考文档references/environment-and-storage-hygiene.md5.8 KB
- 参考文档references/error-pattern-dictionary.md4.6 KB
- 参考文档references/interactive-debugging-and-profiling.md4.1 KB
- 参考文档references/legacy-template.md2.7 KB
- 参考文档references/lifecycle-manual.md1.1 KB
- 参考文档references/public-protocol.md3.5 KB
- 参考文档references/remote-development-and-notebooks.md3.1 KB
- 参考文档references/scheduler-and-parallelism.md5.4 KB
- 参考文档references/slurm-launch-patterns.md6.1 KB
- 参考文档references/software-build-and-reproducibility.md3.1 KB
- 参考文档references/tools-and-scripts.md1.1 KB
03 SKILL.md 正文
HPC Orchestration
Use this skill as the repository-level execution layer above solver-specific HPC skills.
Start
- Read
references/cluster-operations-manual.mdfirst for any end-to-end cluster workflow. - Read
references/lifecycle-manual.mdwhen coordinating solver skills with orchestration stages. - Read
references/scheduler-and-parallelism.mdwhen choosing scheduler directives or MPI sizing. - Read
references/slurm-launch-patterns.mdwhen the main decision is how to launch work inside a Slurm allocation. - Read
references/environment-and-storage-hygiene.mdwhen environment modules, scratch policy, or filesystem behavior may decide workflow reliability. - Read
references/data-transfer-and-staging.mdwhen files must be synchronized, staged, archived, or verified. - Read
references/software-build-and-reproducibility.mdwhen compilation, package stacks, or rebuildability are in scope. - Read
references/interactive-debugging-and-profiling.mdwhen the task needs live diagnosis, scaling studies, or profiler evidence. - Read
references/remote-development-and-notebooks.mdwhen VS Code Remote SSH, Jupyter, or port forwarding is involved. - Read
references/container-workflows.mdwhen Apptainer or Singularity-style execution is in scope. - Read
references/public-protocol.mdwhen aligning solver skills with the repository lifecycle contract. - Read
references/error-pattern-dictionary.mdwhen scheduler, monitoring, or log-tracking failures occur.
Additional References
Load these on demand:
references/tools-and-scripts.mdfor shared execution tool rolesreferences/ecosystem-roadmap.mdfor repository-wide coverage goalsreferences/legacy-template.mdwhen adapting an older solver skill draft into the current format
Reusable Templates
Use assets/templates/ when a concrete scheduler scaffold is needed:
slurm-basic.shslurm-array.shslurm-packed-single-node.shslurm-apptainer.shslurm-perf-report.shpbs-basic.shlsf-basic.shrsync-stage-in.shjupyter-lab-compute.shssh-config-compute-proxy.example
Shared Scripts
Use scripts/ for deterministic orchestration tasks:
hpc_job_submitter.pyhpc_job_monitor.pyhpc_log_tracker.pyhpc_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.
04 同仓库更多 Skills
dei-assessment
Assess diversity, equity, and inclusion with metrics. TRIGGERS - Use when user needs help with dei-assessment related tasks.
dei-action-plan
Create DEI action plans with goals and initiatives. TRIGGERS - Use when user needs help with dei-action-plan related tasks.
culture-fit-assessment
Design culture add assessment processes. TRIGGERS - Use when user needs help with culture-fit-assessment related tasks.
cowork-to-code-bridge
Use an already-installed, independently verified cowork-to-code bridge to run narrowly approved actions on the user's own macOS, Linux, or WSL2 machine through a local file queue.
counter-offer-response
Draft counter-offer responses for retention. TRIGGERS - Use when user needs help with counter-offer-response related tasks.
continuous-feedback-system
Design continuous feedback systems. TRIGGERS - Use when user needs help with continuous-feedback-system related tasks.