Set up cross-cluster SSH (Great Lakes <-> Lighthouse) and establish the connection. Handles first-time setup automatically.
Experimental. Plan and assist migration of a repository to another lab's compute resources by discovering the current server, user, Slurm/storage environment, and repo assumptions, then presenting findings for correction before editing.
Submit a SLURM experiment with proper naming, documentation, and cross-cluster support. Reads project context to discover submission infrastructure.
Discover completed SLURM experiments, collect results, and update experiment documentation.
Onboard a lab member onto the shared Claude Code and/or Codex configuration. Detects clusters, collects Slurm account details, runs setup, and helps customize personal config.
Onboard a new lab member onto the shared Claude Code configuration. Detects clusters, collects Slurm account details, runs setup, and helps customize personal config.
Create or modify an sbatch job script with correct partitions, accounts, GPU requests, and best-practice defaults for the current cluster.
Diagnose why a Slurm job failed, was killed, or is stuck pending. Reads job metadata, logs, and common error patterns to explain what went wrong and how to fix it.