hpc skills

68 tagged hpc, measured the same way as everything else here.

Browse within: ai4hpc 60ai4science 60hpc-ai 60mcp-tools 60browser-automation 21gemini 20Optimization 19simulations 19academic-writing 11bibliography 11citation-analysis 11auto-tuning 10multiagent 10opencode 10

budget-tracking

01

Katagiri-Hoshino-Lab/VibeCodeHPC

Skill Claude Code

Compute budget management with phase-based termination criteria. Use when checking budget, determining project phase, or making stop decisions.

not rated 42 2d ago A 27 tokens original MIT

dense-evolution-mcp

02

tatopenn-cell/Dense-Evolution

Skill Claude Code

Drive Dense-Evolution's real quantum circuit simulator, VQE solver, molecular Hamiltonian builder, QM/MM force calculator, and MD trajectory engine directly through the denseevolutionmcp MCP server, instead of writing new simulation code or describing what a circuit should do in the abstract. Use this skill whenever…

not rated 17 yesterday A 165 tokens

cpp-oop-style

03

archibate/agent-skills

Skill Codex

High-quality C++ OOP coding style (archibate / parallel101 lineage) that overrides sloppy AI-default C++. Use this skill WHENEVER writing, editing, refactoring, or reviewing C++ code (.cpp / .h / .hpp / .cc / .cxx), designing C++ classes, interfaces, APIs, or libraries, or when the user mentions C++ design, OOP…

not rated 13 +2 changed 11d ago A 140 tokens

optimize-report

04

TaoELi/FermiLink

Skill Claude CodeCodex

Generate a Sphinx-ready report bundle (plots, RST, contract, per-accepted-commit pages) from a completed fermilink optimize workspace. Use when the user asks to visualize, export, or publish optimization results from a .fermilink-optimize directory, or wants to prepare material for the Project Optimization website.

not rated 11 1mo ago A 73 tokens AGPL-3.0

chgagne/claude-skills-research

Skill Claude CodeCodex

Use when asked to review, critique, or assess an academic paper from its LaTeX sources — including pre-submission critique of a student's or collaborator's draft, or a referee report for a venue. Also when the only artifact is a blind PDF with no sources. Triggers on "review this paper", "assess the paper", "read my…

not rated 5 changed 20d ago A 119 tokens original MIT

awaitless

06

xpluspro/Awaitless

Skill Codex

Run non-interactive builds, tests, benchmarks, and local, SSH, or Slurm commands through Awaitless's adaptive durable execution layer. Use by default when command duration is uncertain, work may outlive the current turn, a named scarce resource may be queued, multiple jobs should complete without polling, or bounded…

not rated 1 1mo ago A 73 tokens original MIT

dtu-hpc

07

PV-Bhat/dtu-hpc-mcp

Skill Claude CodeCodex

Operate the DTU HPC cluster (DCC, LSF) through the dtu-hpc MCP connector. Invoke BEFORE any cluster work — submitting or monitoring jobs, checking queues or quotas, planning GPU experiments, fetching logs or artifacts, or diagnosing failed runs on DTU HPC. Covers queue selection, job chaining past the 24h walltime…

not rated 0 2mo ago A 88 tokens original MIT

project-bourne

08

KozakHou/project-bourne

Skill Codex

Use Project Bourne to plan, execute, reproduce, inspect, or trace scientific and engineering workloads when durable provenance matters. Trigger for simulations, numerical solvers, ML or training, GPU and HPC runs on local compute, Slurm, PBS, or LSF, reproducible experiments, failed attempts, experiment comparisons…

not rated 0 1mo ago A 91 tokens original Apache-2.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: