lawrencium-hpc

Get a 12-hour Lawrencium SSH certificate for lrc-login from a /lrc-cert pane in Claude Code (username, PIN and OTP).

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

All hpc deployment skills.

24 skills

Parallelize large-scale geospatial operations on a single fat node — tile-edge dissolve, polygon elimination, polygonize, spatial joins, reprojection, simplification — at national/continental scale (10–100M polygons). Use when speeding up or designing a geospatial batch process, or as a pre-flight checklist for known failure modes (DuckDB GEOS segfaults, topology exceptions, int64 overflow, NFS thrashing).

1 skill

Integrate DTensor-based context parallelism (CP) into a custom co-folding / structure-prediction model — sharding the O(N²) pair and attention tensors across a multi-GPU device mesh via explicit ring/transpose collectives. A top-level cpize_model_workflow conductor prioritizes, sequences, and gates the whole effort end-to-end, delegating each phase to focused skills. Explores the user's model and data pipeline, builds and probes distributed test infrastructure (local GPUs or SLURM), implements DTensor data-feature sharding and CP model modules mapped to a located CP reference implementation (e.g. Boltz-CP, via $BOLTZ_CP_REPO), writes serial-as-ground-truth multi-rank parity tests, dispatches the work across an orchestrated coder+reviewer team, and benchmarks max-token / walltime. Ships a SessionStart hook that injects the CP hard-rules and an opt-in PreToolUse guard protecting serial ground-truth files and distributed-test timeouts.

10 skills · hooks

Integrate scientific training code into itwinai: distributed training, HPO, logging, profiling and scalability reports

1 skill