Deep learning

A skill your agent uses when writing, debugging, porting, reviewing, or optimizing CUDA C++ or PTX kernels; investigating CUDA Runtime or Driver API behavior; profiling kernels with Nsight Systems…

vipshop/cache-dit

Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab).

wanshuiyin/ARIS-in-AI-Offer

Shows how to organize PyTorch training with Lightning's LightningModule and Trainer, covering validation, DDP, callbacks and learning-rate scheduling.

Orchestra-Research/AI-Research-SKILLs

Create, modify, and improve PINA skills. An agent skill from PINA-org/PINA.

PINA-org/PINA

PaddlePaddle (飞桨) C++ 算子开发指南。提供从 YAML 配置、InferMeta 函数、Kernel 实现、Python API 封装、单元测试到编译验证的完整算子开发流程指导。在以下场景使用此 skill：(1) 为 Paddle 框架新增 C++ 算子 (2) 修改或调试已有 Paddle 算子 (3) 编写算子的 YAML…

PaddlePaddle/Paddle

Policy for AlbumentationsX transforms that combine multiple images or objects.

albumentations-team/AlbumentationsX

Rigor Setup skill for README-first deep learning repo reproduction.

lllllllama/RigorPilot-Skills

Looks up public original architecture diagrams for named LLM, vision-language, MoE, diffusion and OCR models and returns the image with its source attribution.

BBuf/AI-Infra-Auto-Driven-SKILLS

Shows how to launch distributed Megatron-LM training on a SLURM cluster: sbatch skeleton, torch.distributed.run setup, CUDA_DEVICE_MAX_CONNECTIONS rules and failure diagnosis.

NVIDIA/Megatron-LM

A skill your agent uses when optimizing or generating a CUDA megakernel for a HuggingFace Llama-family model with AutoMegaKernel (AMK), drives the correctness-gated propose - eval - keep/revert loop…

RightNow-AI/AutoMegaKernel

Refresh GitNexus indexing and regenerate local GitNexus skills when repository status is stale.

ML4ITS/TimeVQVAE

Inspect a PyTorch baseline with torch.compile graphs/code and torch.profiler before drafting a custom kernel, then compare TileLang and PyTorch timelines, forward/backward regions, and allocations.

sablin39/tilelang-cuda-skills

Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility.

pytorch/pytorch

Run Python unit test suites strictly using the uv package manager and pytest.

brendanhasz/probflow

Inspect and compare PyTorch models with TorchScan reports, operator FLOPs, and peak-memory workloads.

frgfm/torch-scan

Run flexynesis, a deep-learning suite for multi-omics data integration and clinical outcome prediction (drug response, cancer subtyping, survival analysis).

BIMSBbioinfo/flexynesis

Render an ARIS Markdown / JSON artifact (IDEAREPORT, AUTOREVIEW, KILLARGUMENT, PAPERPLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading.

wanshuiyin/ARIS-in-AI-Offer

Orchestrates a complete session from problem definition through trained solver.

PINA-org/PINA

Guide for debugging distributed training issues in AReaL. An agent skill from areal-project/AReaL.

areal-project/AReaL

Fixes tool environment setup failures in proto-tools, either just for the current machine (eject the tool's standalone dir, patch it, and point PROTO<TOOLKITSTANDALONEDIR at it; works for any…

evo-design/proto-tools

Rigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories.

lllllllama/RigorPilot-Skills

Helps build, test and extend the Qualcomm AI Engine Direct (QNN) backend in ExecuTorch, with routes for new ops, model export, Buck-vs-CMake parity fixes and per-layer accuracy debugging.

pytorch/executorch

Solutions for non-trivial PerforatedAI integration scenarios.

PerforatedAI/PerforatedAI

Submit, monitor and benchmark jax-gcm (jcm) simulations on NCAR Derecho's PBS queues.

climate-analytics-lab/jax-gcm

Preflight checks and diagnosis for ten known failure modes of ML training on NVIDIA DGX Spark's GB10, spanning launch errors, memory, thermals, bandwidth and precision.

wshobson/agents

Debug PyTorch 2 compiler stack failures including Dynamo graph breaks, Inductor codegen errors, AOTAutograd crashes, and accuracy mismatches.

pytorch/pytorch

Guides training and analyzing sparse autoencoders with SAELens to break neural network activations into interpretable features, including superposition and monosemanticity studies.

Orchestra-Research/AI-Research-SKILLs

Fine-tune or transfer-learn AlphaGenome-PyTorch on custom genomic data — pick a mode (linear probe, LoRA, Locon, full), train on BigWig tracks with agt finetune, use adapters, delta checkpoints…

genomicsxai/alphagenome-pytorch

自动创建或更新 GitHub Pull Request. An agent skill from PaddlePaddle/Paddle.

PaddlePaddle/Paddle

A skill your agent uses when writing, reviewing, or debugging JAX code that involves quax — custom array-ish objects (physical units, LoRA, sparse, symbolic zero, named axes), quax.quaxify…

nstarman/quax

Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab.

JimLiu/science-skills

Advisory guidance for Amazon EKS architecture and configuration decisions — compute strategy, networking, security, reliability, cost, autoscaling, observability, multi-tenancy, and upgrade planning.

aws-samples/appmod-blueprints

Guides users through selecting, configuring, or creating a PyTorch model for a PINA problem.

PINA-org/PINA

Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories.

lllllllama/RigorPilot-Skills

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP).

Orchestra-Research/AI-Research-SKILLs

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction.

Orchestra-Research/AI-Research-SKILLs

Research why neural architectures and training methods work through forward computation, geometry, gradients, optimization dynamics, historical experiments, and competing explanations.

shareAI-lab/lab-skills

Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs).

K-Dense-AI/mimeo

HuggingFace Transformers integration for PerforatedAI. An agent skill from PerforatedAI/PerforatedAI.

PerforatedAI/PerforatedAI

Make behavior changes using this repository's lightweight spec-driven flow.

gdsfactory/sax

Systematic performance audit for AlbumentationsX runtime code.

albumentations-team/AlbumentationsX

Fetch, analyze, reproduce, and minimize GitHub issue reproductions.

pytorch/pytorch

Ensure consistent code formatting using the uv package manager and pre-commit.

brendanhasz/probflow

Run AlphaGenome-PyTorch to get genomic track predictions — via the agt predict CLI (single locus, BED regions, whole chromosomes, raw FASTA sequences, or per-gene count tables/AnnData), variant…

genomicsxai/alphagenome-pytorch

Cloud-based quantum chemistry platform with Python API. An agent skill from lamm-mit/scienceclaw.

lamm-mit/scienceclaw

Adds distributed and mixed-precision training to a PyTorch script with a few Accelerate lines, then launches it on one GPU, many GPUs or DeepSpeed and FSDP setups.

Orchestra-Research/AI-Research-SKILLs

Launch a Qualitative Neural Network (QNN) — a layered, multi-epoch brainstorm of agent personas that maps divergent strategies before implementation.

iblameandrew/open-deepthink

Build and debug cuEquivariance irreps, custom Irrep subclasses, Clebsch-Gordan tensor products, and equivariant or segmented polynomials.

NVIDIA-BioNeMo/bionemo-agent-toolkit