How do I install the Hpc Foundations skill?

Run npx skillmds@latest add scimate-ai/hpc-foundations 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 Foundations 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 Foundations?

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 Foundations free to use?

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

Who published Hpc Foundations?

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

Hpc Foundations by scimate-ai — Agent Skill

Name: Hpc Foundations
Author: scimate-ai

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 workflows, software environment setup, storage or network fundamentals, or when turning general HPC knowledge into future skills.

scimate-ai c15537b 10 files · 35.7 KB Updated Sep 17, 2026

File contents

HPC Foundations

Use this skill as the general HPC knowledge hub that sits below solver-specific skills and beside hpc-orchestration.

Start

Read references/index-map.md first for the knowledge graph and the shortest route to the right topic.
Read references/foundations-architecture-and-programming.md when the task starts from HPC concepts, system design, programming models, application development, or performance basics.
Read references/schedulers-and-execution.md when the task is about Slurm, PBS Pro, LSF, queue semantics, batch scripts, arrays, or accounting commands.
Read references/linux-and-os.md when the task is about Linux usage, login patterns, package management, glibc compatibility, or Linux versus Windows tradeoffs on clusters.
Read references/software-environments.md when the task is about Conda, containers, Singularity or Apptainer-style execution, or picking common HPC tools.
Read references/storage-network-cloud-and-admin.md when the task is about storage tiers, RDMA, hardware, cloud deployment, SSL, Hyper-V maintenance, or site-level administration topics.
Read references/source-catalog.md when a page-level lookup of the hpclib.com crawl is needed.
Read references/skillization-roadmap.md when splitting this index into narrower reusable skills.

Positioning

Prefer this skill for orientation, taxonomy, and first-pass explanation.
Prefer hpc-orchestration once the question becomes an execution workflow on a real cluster.
Prefer solver-specific skills once the question becomes input-deck or application specific.

Guardrails

Treat hpclib.com as a practical knowledge index, not as the final authority for production commands.
Re-check scheduler flags, MPI launch syntax, package names, and admin procedures against official upstream documentation before applying them on a live cluster.
Do not assume cluster policies, filesystem layouts, or security rules are portable across sites.

---name: hpc-foundationsdescription: 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 workflows, software environment setup, storage or network fundamentals, or when turning general HPC knowledge into future skills.---# HPC FoundationsUse this skill as the general HPC knowledge hub that sits below solver-specific skills and beside `hpc-orchestration`.## Start1. Read `references/index-map.md` first for the knowledge graph and the shortest route to the right topic.2. Read `references/foundations-architecture-and-programming.md` when the task starts from HPC concepts, system design, programming models, application development, or performance basics.3. Read `references/schedulers-and-execution.md` when the task is about Slurm, PBS Pro, LSF, queue semantics, batch scripts, arrays, or accounting commands.4. Read `references/linux-and-os.md` when the task is about Linux usage, login patterns, package management, glibc compatibility, or Linux versus Windows tradeoffs on clusters.5. Read `references/software-environments.md` when the task is about Conda, containers, Singularity or Apptainer-style execution, or picking common HPC tools.6. Read `references/storage-network-cloud-and-admin.md` when the task is about storage tiers, RDMA, hardware, cloud deployment, SSL, Hyper-V maintenance, or site-level administration topics.7. Read `references/source-catalog.md` when a page-level lookup of the hpclib.com crawl is needed.8. Read `references/skillization-roadmap.md` when splitting this index into narrower reusable skills.## Positioning- Prefer this skill for orientation, taxonomy, and first-pass explanation.- Prefer `hpc-orchestration` once the question becomes an execution workflow on a real cluster.- Prefer solver-specific skills once the question becomes input-deck or application specific.## Guardrails- Treat hpclib.com as a practical knowledge index, not as the final authority for production commands.- Re-check scheduler flags, MPI launch syntax, package names, and admin procedures against official upstream documentation before applying them on a live cluster.- Do not assume cluster policies, filesystem layouts, or security rules are portable across sites.

Frequently asked questions