Deep learning

Graph Neural Networks (PyG). An agent skill from davila7/claude-code-templates.

davila7/claude-code-templates

PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.

affaan-m/ECC

Query CZ CELLxGENE Census (61M+ cells). An agent skill from davila7/claude-code-templates.

davila7/claude-code-templates

Graph-based drug discovery toolkit. An agent skill from davila7/claude-code-templates.

davila7/claude-code-templates

PyTorch training reference: architecture choice by data type, scaling rules, a training loop, optimizer and learning-rate choices, and fixes for loss spikes or OOM.

Orchestra-Research/AI-Research-SKILLs

Author a new ShapeShifter graph-transformation pass for AMD Quark (ONNX or PyTorch) so it conforms to the pass framework's conventions and auto-registers.

amd/Quark

End-to-end AscendC custom operator development for Ascend NPU in an ascend-kernel (csrc/ops + build.sh + torchnpu PyTorch custom op) project.

ascend-ai-coding/awesome-ascend-skills

Manage tensor lifetimes across CUDA streams and decide whether recordstream is avoidable.

pytorch/pytorch

Cross-platform Python library for quantum computing, quantum machine learning, and quantum chemistry.

davila7/claude-code-templates

Write optimized Triton GPU kernels for deep learning operations.

vipshop/cache-dit

Measure jcm throughput reproducibly — short (1 month) or long (12 month) runs on a validated stable config, with GPU memory/utilisation logging and an explicit convergence criterion.

climate-analytics-lab/jax-gcm

A skill your agent uses when building ML/AI apps in Rust. An agent skill from moeru-ai/auv.

moeru-ai/auv

How to get debug output out of OCANNL: kernel/routine runtime logs, generated code artifacts, and ppxminidebug tracing of library internals such as the shape/row solver.

ahrefs/ocannl

how to use the edit command properly

omegaml/omegaml

Pre-flight checklist for long-running ML training jobs covering config diff, run naming, path verification, monitoring setup, and restart-cleanup.

fcakyon/phd-skills

Molecular featurization for ML (100+ featurizers). An agent skill from davila7/claude-code-templates.

davila7/claude-code-templates

Create publication-quality scientific diagrams, flowcharts, and schematics using Python (graphviz, matplotlib, schemdraw, networkx).

jimmc414/Kosmos

Rigor Debug / Rigor Audit skill for deep learning research work.

lllllllama/RigorPilot-Skills

Analyze PerforatedAI training results and provide optimization recommendations.

PerforatedAI/PerforatedAI

Disable or re-enable Cloudflare R2 (download-r2.pytorch.org) usage in managev2.py during R2 outages.

pytorch/test-infra

Maintain AlbumentationsX license, CLA, provenance notices, and packaged legal artifacts consistently.

albumentations-team/AlbumentationsX

Import PyTorch, ONNX, or Keras 3 / TensorFlow 2.16+ deep learning models into MATLAB as dlnetwork objects.

matlab/matlab-agentic-toolkit

Run the CLOSED training loop on a MOSS/duck policy without a human having to ask "is it done yet": launch through the lab, block until the run finishes, print the standard report and the per-term…

jonathanhawkins/microduck-lab

Collect and normalize environment facts (OS, Python, GPU, CUDA/ROCm, container state) before Quark installation or PTQ planning.

amd/Quark

Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation.

ascend-ai-coding/awesome-ascend-skills

Fine-tune LLM models using LoRA on OCI AI Quick Actions (AQUA).

oracle/accelerated-data-science

Update the Primus documentation for a monthly training-image release — bump version references, realign the bare-metal install scripts with the release Dockerfiles, record the published image stacks…

AMD-AGI/Primus

Adds PyTorch FSDP2 (fullyshard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing.

Orchestra-Research/AI-Research-SKILLs

Guide for writing and modifying NKI kernels. An agent skill from uw-syfi/vibesys.

uw-syfi/vibesys

Builds Triton-Ascend kernels that pack sorted token assignments into fixed expert-capacity tensors, restore top-k outputs and compute router-weight gradients on Ascend NPUs.

Krusty84/triton-ascend-agent-dev-kit

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks.

davila7/claude-code-templates

分析当前仓库 Pull Request 的失败 CI，基于完整日志和精确 PR diff 定位根因，区分代码问题、环境问题和不稳定问题。

PaddlePaddle/Paddle

Benchmarks LLM inference and drives GPU kernel optimization with Magpie.

amd/skills

Adds support for a new MoE language model to PithTrain. An agent skill from mlc-ai/pith-train.

mlc-ai/pith-train

Review PyTorch upstream unit-test (UT) PRs that enable Intel GPU (XPU) on existing tests.

intel/torch-xpu-ops

Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement.

K-Dense-AI/claude-scientific-writer

Identify domains, families, and sites in proteins; find all proteins in a family or sharing a domain; explore species distribution for a domain; annotate genomes with protein families and GO terms.

google-deepmind/science-skills

Learn the target framework from enabled knowledge tools and implement a baseline GPU kernel.

alibaba/atrex-kernel-agent

Find reverts that landed on pytorch/pytorch main but are missing from a release branch (release/X.Y) because the reverted commit was already shipped in a release candidate, and open one cherry-pick…

pytorch/test-infra

Set up conditions for PINA problems. An agent skill from PINA-org/PINA.

PINA-org/PINA

After completing code changes, runs tests and pre-commit, then iteratively fixes failures until all pass.

albumentations-team/AlbumentationsX

Optimize or review eager CPU-only Albucore PyTorch runtime paths with benchmark-backed decisions.

albumentations-team/albucore

pyqula's CPU/GPU switch (src/pyqula/gpu.py), how a routine is routed onto the device, per-call precision, and the tiered porting plan in documentation/gpuportingplan.md.

joselado/pyqula

Install or verify the AMD Quark package and its dependencies.

amd/Quark

Build and train variational quantum algorithms (VQE, QAOA, QML, QNN) with MindQuantum.

mindspore-ai/mindquantum

WandB-specific PerforatedAI integration guardrail skill. An agent skill from PerforatedAI/PerforatedAI.

PerforatedAI/PerforatedAI

Run the jax-gcm CI gates locally on Derecho when GitHub Actions minutes are exhausted or a pre-push check is wanted — lint, fast tests (90% coverage), slow tests (80% PR coverage) and a local Claude…

climate-analytics-lab/jax-gcm

Guides building a FlashAttention-v2-style fused forward attention kernel for Triton-Ascend on Ascend NPU, with online softmax, causal staging and float32 accumulation.

Krusty84/triton-ascend-agent-dev-kit