---
title: "hpc-rikyu"
description: "Facility-specific HPC workflow skills for RIKYU (RIKEN AI4S / GB200). Install the hpc base plugin first for MCP tools."
canonical: https://agentpluginsdirectory.com/plugins/hpc-rikyu
last-updated: 2026-10-21
---

# hpc-rikyu
Facility-specific HPC workflow skills for RIKYU (RIKEN AI4S / GB200). Install the hpc base plugin first for MCP tools.
- Slug: hpc-rikyu
- Publisher: William Dawson
- Repository: https://github.com/william-dawson/hpc-rookery
- Manifest: plugins/hpc-rikyu/plugin.json
- Version: 0.1.1
- Category (editorial): other
- Skills: 7 (rikyu-configuring, rikyu-demo, rikyu-monitoring-jobs, rikyu-reference, rikyu-remote-command, rikyu-reproducing, rikyu-submitting-jobs)
- MCP servers: 0
- Stars: 2
- Repository created: 2026-10-13
- Repository last pushed: 2026-10-13
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/hpc-rikyu
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## Skills

- rikyu-configuring: Use when the user wants to set up, configure, or troubleshoot RIKYU (RIKEN AI4S / GB200), SSH access, 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-demo: Interactive demo of RIKYU (RIKEN AI4S / GB200), walks through configuration, facility info, live cluster status, docs search, filesystem access, and a real job end to end.
- rikyu-monitoring-jobs: Use when the user asks about the status, progress, output, history, or failure of jobs on RIKYU (RIKEN AI4S / GB200), or about queue and node availability. Also use this any time you (the agent) need to check on or wait for a job you submitted, even without a fresh user request.
- rikyu-reference: Use to answer questions about RIKYU (RIKEN AI4S / GB200) itself, hardware, partitions, storage, software, policies, or where to get help. Ground answers in the bundled guide and live tool output rather than prior knowledge.
- rikyu-remote-command: Use when the user wants to run one or more shell commands on RIKYU (RIKEN AI4S / GB200)'s login node, or when another workflow needs run_command_on_cluster for a live check not covered by a safer typed tool. Requires an exact command preview and explicit user permission before execution.
- rikyu-reproducing: Use when the user asks to make a result on RIKYU (RIKEN AI4S / GB200) 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 workflow vi…
- rikyu-submitting-jobs: Use when the user wants to run, submit, or launch a job on RIKYU (RIKEN AI4S / GB200). Covers partition/queue selection, JobSpec construction, submission, and known gotchas specific to this facility.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.