Build finite-volume models on finitevolX (Arakawa C-grid stencils and operators, masks, boundary conditions, advection, elliptic solvers, time steppers) instead of re-implementing them: a model-building skill and a reuse reviewer.
Plugin finitevolx from marketplace finitevolx in jejjohnson/finitevolX. Commands read from the repo's manifest — 3 days ago.
finite-volume-models-with-finitevolxWrite finite-volume ocean and atmosphere models in JAX on finitevolX — Arakawa C-grids with a ghost ring (Cartesian and spherical, 1-D / 2-D / 3-D, multilayer), raw stencils and difference / interpolation / divergence / vorticity operators, WENO / TVD / upwind advection, diffusion, Coriolis and mome
finitevolx-reuse-reviewerRead-only reviewer for JAX projects that use (or could use) finitevolX. Checks a diff or a set of files for finite-volume code that re-implements what finitevolX already provides — shifted-slice differences and averages on a staggered grid, ghost-cell fills, wet / dry face masks, upwind / WENO / TVD
Create finite-volume meshes and discrete differential operators with discretize. Use for TensorMesh or TreeMesh geometry, cell/face/edge ordering, divergence, interpolation and meshes supporting SimPEG; use a physics solver for inversion itself.
48 skills · 3 agents
Comprehensive machine learning expertise across training, evaluation, deployment, MLOps, data pipelines, fine-tuning, inference optimization, and cloud ML platforms. PROACTIVELY activate for: (1) any ML task, (2) PyTorch/TensorFlow/JAX/scikit-learn/XGBoost/Hugging Face work, (3) SageMaker/Vertex AI/Azure ML/Databricks/Ray workflows, (4) model serving with Triton/ONNX/TensorRT/BentoML, (5) reproducibility, leakage, drift, monitoring, responsible AI, and cost optimization. Provides: best-practice guidance from data validation through production operations.
9 skills · 1 agent
Teaches agents to run differential expression analysis with delnx: method choice, pseudobulk NB, contrasts, markers, and plots
1 skill
Reproducible Agent Environment: 29 skills for coding standards enforcement, quality gates, repo scaffolding, repo auditing, golden/parity test harnesses, semi-formal code reasoning, ~80% ASD-STE100 technical specifications, GitHub activity review, JAX memory/retracing diagnosis, JAX JIT/fusion hygiene, efficient rendering, ISR MyST scientific paper writing & pre-2026 voice alignment, and domain-specific development (biomechanics, DataJoint, gait analysis, camera models)
27 skills · 1 command · hooks
Codex workflows and architecture, testing, debugging, Python, JAX, Polars, and Rust guidance.
14 skills
Interactive Pallas TPU kernel optimization via an iterative think-submit-analyze-reflect loop on a Cloud TPU VM over SSH. Skills: init-kernel, profile-brief, start, submit, analyze, reflect, transfer.
7 skills
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.