Dask
Provides Dask parallel computing framework for scaling Python workloads across cores and clusters. Covers DataFrames, Arrays, Bags, Delayed, distributed scheduler, GPU acceleration with cuDF/CuPy, and HPC deployment with Dask-Jobqueue.
Mpi
Provides MPI (Message Passing Interface) for parallel and distributed computing. Covers point-to-point communication, collective operations, process management, Open MPI, MPICH, and mpi4py Python bindings for HPC applications.
Qiskit
Provides Qiskit quantum computing framework for building quantum circuits, executing on IBM Quantum hardware and simulators, using runtime primitives (Sampler, Estimator), transpiler optimization, error mitigation, quantum information science, and ecosystem tools including Qiskit Metal for quantum hardware design. Applies to tasks involving quantum circuit construction, quantum algorithms, variat…
Flashinfer
FlashInfer — High-performance kernel library for LLM inference with optimized attention, paged KV-cache, FP8/FP4 quantization
Prime Verifiers
Prime Intellect verifiers & PrimeRL — build RL environments, rubrics, and reward functions for LLM post-training. Covers environment classes, tool integration, GEPA prompt optimization, and async distributed RL training.
Cutile
NVIDIA CuTile Python — tile-based GPU programming DSL. Write kernels using tiles instead of threads, with automatic tensor core and TMA optimization. Blackwell GPUs (compute 10.x/12.x).
Autoresearch Setup
Scaffold an autoresearch-style autonomous experiment loop for any domain. Generates program.md, fixed evaluation harness, mutable experiment file, and results logging — inspired by Karpathy's autoresearch philosophy.
Polars
Polars DataFrame library with GPU acceleration via RAPIDS cuDF — lazy evaluation, expressions API, and high-performance data transformations
Triton
Triton — Python-like language for writing high-performance GPU kernels with automatic optimization, block-based programming, tensor cores
Materials Project
Materials Project API — access 150k+ computed materials, crystal structures, thermodynamics, electronic/phonon properties via MPRester and pymatgen
Rdkit
RDKit cheminformatics toolkit — molecular I/O, descriptors, fingerprints, substructure searching, reactions, and 3D conformer generation
Biosimspace
BioSimSpace — engine-agnostic Python framework for biomolecular simulation. Portable workflows across AMBER, GROMACS, NAMD, OpenMM. Parameterisation, solvation, minimisation, equilibration, production MD, free energy perturbation, metadynamics.
Omniverse Simready
NVIDIA Omniverse SimReady — OpenUSD standard for physically accurate 3D assets with metadata for robotics, digital twins, synthetic data generation
Ray
Provides Ray distributed computing framework for scaling Python applications. Covers Ray Core (tasks, actors, objects), Ray Data (data processing), Ray Train (distributed training), Ray Serve (model serving), Ray Tune (hyperparameter tuning), and Ray RLlib (reinforcement learning).
Alchemi Toolkit Ops
Provides NVIDIA ALCHEMI Toolkit-Ops patterns for GPU-accelerated atomistic simulation kernels. Applies to tasks involving neighbor list construction, electrostatic interactions (Ewald, PME, Coulomb, multipole), DFT-D3 dispersion corrections, molecular dynamics, GNN-based molecular property prediction, or high-throughput computational chemistry on NVIDIA GPUs.
Tinker
Tinker by Thinking Machines Lab — low-level training API for LLM fine-tuning. LoRA training, RL environments, supervised learning, DPO, and custom loss functions with full algorithmic control over remote GPU clusters.
Nemotron
NVIDIA Nemotron — open LLM family with hybrid Mamba-Transformer MoE architecture, 1M context, NIM deployment, synthetic data generation
Bionemo
Provides NVIDIA BioNeMo patterns for computational biology and AI-driven drug discovery. Applies to tasks involving protein language models (ESM-2), structure prediction (AlphaFold2), protein design (RFdiffusion, ProteinMPNN), molecular generation, NIM microservice deployment, or multi-model biology pipelines.
Cuda Quantum
Provides CUDA-Q hybrid quantum-classical programming patterns for GPU-accelerated quantum simulation, circuit construction, variational algorithms, hardware backend configuration, dynamics simulation, and CUDA-QX extension libraries (solvers for molecular chemistry, QEC for error correction). Applies to tasks involving quantum kernels, qubit operations, cuQuantum simulation, VQE/QAOA optimization…
Slurm
Provides Slurm Workload Manager commands for HPC cluster job scheduling, GPU allocation with GRES, job arrays, MPI integration, resource management, QOS configuration, and accounting. Applies to tasks involving batch job submission (sbatch), interactive jobs (srun, salloc), job monitoring (squeue, sacct), GPU/CUDA workloads, parallel computing, cluster resource allocation, or HPC workflow managem…
Physicsnemo
Provides NVIDIA PhysicsNeMo patterns for building, training, and deploying physics-informed machine learning models at scale. Applies to tasks involving neural operators (FNO, AFNO), weather/climate modeling (FourCastNet, CorrDiff, GraphCast), scientific simulation surrogates, physics-constrained training, or distributed GPU training for scientific AI.
Validate Skills
Validates skills in this repo against agentskills.io spec and Claude Code best practices. Use via /validate-skills command.