fugaku
claudecodexPJM (pjsub/pjstat/pjdel) job management, filesystem operations, and documentation search for the RIKEN Fugaku supercomputer
7 skills · 2 MCP servers
Slurm job management, filesystem operations, and documentation search for the RIKEN AI4S supercomputer (NVIDIA GB200, aarch64)
Plugin rikyu from marketplace hpc-agentic-sdk in RIKEN-RCCS/HPC-Agentic-SDK. Commands read from the repo's manifest — 24 days ago.
This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.
rikyu-configuringUse when the user wants to set up, configure, or troubleshoot RikyuAgent — SSH access to the Rikyu cluster, the embedding endpoint for docs search (RAG), or the ~/.hpc-agent/rikyu.json file. Also use when rikyu tools fail with connection or embedding errors.
rikyu-demoInteractive demo of RikyuAgent — walks through facility info, live cluster status, docs search, filesystem access, and job submission on the RIKEN Rikyu supercomputer.
rikyu-monitoring-jobsUse when the user asks about the status, progress, output, history, or failure of jobs on the Rikyu supercomputer, or about queue and node availability.
rikyu-referenceUse when answering any question about Rikyu supercomputer specifics — login, accounts, partitions, modules, storage, policies — or when unsure about a cluster detail. Search the bundled guide instead of guessing.
rikyu-reproducingUse when the user asks to make a result reproducible, shareable, or turned into a notebook/script — or proactively suggest it after a chunk of exploratory job/file work that produced something worth preserving. Builds a Jupyter notebook that replays the real Rikyu workflow via hpc_agent_core.client,
rikyu-submitting-jobsUse when the user wants to run, submit, or launch a job (training, computation, benchmark) on the Rikyu supercomputer. Covers partition selection, JobSpec construction, submission, and interactive sessions.
rikyu-hpcruns: uv tool run --quiet --from git+https://github.com/RIKEN-RCCS/Rikyu-Agent.git@main#subdirectory=server rikyu-hpc-mcp
rikyu-docsruns: uv tool run --quiet --from git+https://github.com/RIKEN-RCCS/Rikyu-Agent.git@main#subdirectory=server rikyu-docs-mcp
PJM (pjsub/pjstat/pjdel) job management, filesystem operations, and documentation search for the RIKEN Fugaku supercomputer
7 skills · 2 MCP servers
Slurm job management, filesystem operations, and documentation search for the RIKEN HOKUSAI BigWaterfall2 (HBW2) supercomputer
6 skills · 2 MCP servers
Slurm job management, filesystem operations, and documentation search for the RIKEN R-CCS Cloud (heterogeneous: A64FX, x86_64, NVIDIA/AMD/Intel GPUs)
6 skills · 2 MCP servers
Expose Makefile targets as MCP tools for building and running code on local or remote HPC systems via SLURM
1 skill · 1 MCP server
Check whether loop transformations (interchange, tiling, fusion) are mathematically safe using polyhedral analysis
1 skill · 1 MCP server
Use and contribute to BenchKit, a shell-first framework for building and running HPC benchmarks across multiple systems
1 skill
SkyPilot agent skill for launching cloud VMs, Kubernetes pods, and Slurm jobs across 25+ clouds
1 skill
Comprehensive Python programming reference covering syntax, concurrency, networking, databases, ML/LLM development, and HPC
2 skills
General life-sciences research workflows with query routing, evidence synthesis, and optional parallel subagent analysis across genetics, omics, biology, chemistry, structure, clinical evidence, and public dataset discovery.
50 skills
Cross-profession skills: Press Release, Grant Proposal, Executive Summary, Teaching Lesson Plan, Sycophancy Challenger, Last 30 Days Research, NotebookLM Connector, Professional Brain, Action Runner. Get genuine push-back on your ideas, gather multi-platform research, automate NotebookLM — plus the Professional Brain: a durable local memory skills read & write back (provenance-tagged), and Action Runner to execute a skill's recommendations (open tickets, post updates) safely behind a dry-run approval gate.
11 skills
Twelve-skill bundle covering the American Educational Research Journal (AERJ) manuscript lifecycle across quantitative, qualitative, and mixed-methods education research and the journal's two sections (Social and Institutional Analysis; Teaching, Learning, and Human Development).
12 skills
A gated mathematical-modeling contest workflow with human-owned decisions and submission audits.
29 skills · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.