Deep learning

Guides mechanistic interpretability work with TransformerLens: loading models, caching activations, using HookPoints, activation patching and attention-pattern analysis.

Orchestra-Research/AI-Research-SKILLs

Step-by-step playbook for migrating a pytorch/pytorch .github/workflows/.yml from EC2 to OSDC (ARC) runners — covers both dial-up and 100% opt-in patterns, with the inputs that must be plumbed…

pytorch/test-infra

Guides users through selecting the right PINA solver for their problem, or creating a custom solver when no built-in fits.

PINA-org/PINA

QAI ModelBuilder. An agent skill from qualcomm/qai-appbuilder.

qualcomm/qai-appbuilder

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

lllllllama/RigorPilot-Skills

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/Auto-claude-code-research-in-sleep

Call this skill when you need to debug CUDA crashes in SGLang using kernel API logging

sgl-project/sglang

Guide for using MPK test mode to unit-test individual layers or multi-layer pipelines through the full compilation pipeline.

mirage-project/mirage

将原生 PyTorch 自定义算子库、Torch extension、生态库（TorchCodec/FlashInfer/DeepEP 等）以及 Kernel DSL 生态（Triton/TileLang/TVM FFI 等）以最小修改方式接入 PaddlePaddle。遇到以下场景务必使用：迁移外部算子库到 Paddle；分析 PFCCLab fork 与上游的兼容差异；处理…

PaddlePaddle/Paddle

A skill your agent uses when reviewing a pull request or diff in the quax repository.

nstarman/quax

Render a single-panel PAI figure of score versus parameter count from sweep CSVs, PAI run folders, or hand-supplied numbers.

PerforatedAI/PerforatedAI

Triages GitHub issues by routing to oncall teams, applying labels, and closing questions.

pytorch/pytorch

Check PyTorch ciflow/xpu (xpu.yml) on the main branch, collect the failing XPU test cases from the most recent completed run(s), analyze the ROOT CAUSE of each failure with AI, and produce a list…

intel/torch-xpu-ops

Analyze single-file PyTorch/Kineto Chrome trace .json(.gz) files using the VeloQ CLI.

lucifer1004/VeloQ

Run, resume, monitor, diagnose, and report Quark Quant-Perf workflows for PyTorch and HuggingFace transformers models.

amd/Quark

Guide users through Cosmos3 supervised fine-tuning (SFT) post-training: preparing the example dataset and Wan2.2 VAE, converting the base checkpoint to DCP, launching distributed training (paired…

NVIDIA/cosmos-framework

Patterns and pitfalls for the ONNX-domain Attention operator's CUDA implementation in ONNX Runtime: dispatch cascade, eligibility limits, mask and bias kernels, and test routing.

microsoft/onnxruntime

Touch-lists for common OCANNL extension tasks: adding a primitive operation, adding or extending a backend, extending shape inference, and diagnosing output differences between backends.

ahrefs/ocannl

Convert PyTorch ATDISPATCH macros to ATDISPATCHV2 format in ATen C++ code.

intel/torch-xpu-ops

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace.

Orchestra-Research/AI-Research-SKILLs

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution.

Orchestra-Research/AI-Research-SKILLs

Guides causal experiments on PyTorch models with pyvene, such as causal tracing, activation patching and interchange intervention training, to test how a model works.

Orchestra-Research/AI-Research-SKILLs

Scales PyTorch, TensorFlow and Hugging Face training from a single GPU to multi-node clusters with Ray Train, including Ray Tune sweeps and checkpoint recovery.

Orchestra-Research/AI-Research-SKILLs

Guides reinforcement-learning research with torchforge, Meta's PyTorch-native library that keeps RL algorithms apart from infrastructure, including GRPO math-reasoning runs.

Orchestra-Research/AI-Research-SKILLs

Sets up large-scale LLM training with NVIDIA Megatron-Core, choosing tensor, pipeline, data, context and expert parallelism for a given model size and GPU count.

Orchestra-Research/AI-Research-SKILLs

Guides users through configuring the PINA Trainer for solver training, including batching strategy, data splitting, and Lightning options.

PINA-org/PINA

Export a PyTorch model to .pte format for ExecuTorch. Use when converting models, lowering to edge, or generating .pte files.

pytorch/executorch

Processes digital pathology whole slide images with histolab: tissue detection, mask creation, tile extraction and dataset preparation for deep learning.

davila7/claude-code-templates

Builds machine learning pipelines on clinical data with PyHealth: EHR datasets, prediction tasks, medical code mapping, healthcare models and evaluation.

davila7/claude-code-templates

Organizes PyTorch training code into LightningModules, DataModules and Trainers, with multi-GPU strategies, callbacks and logging configured.

davila7/claude-code-templates

Deploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder).

matlab/agent-skills-playground

Covers logging and viewing training metrics, histograms, model graphs, embeddings and profiles with TensorBoard in PyTorch and TensorFlow projects.

Orchestra-Research/AI-Research-SKILLs

Rigor Intake helper for README-first deep learning repo reproduction.

lllllllama/RigorPilot-Skills

Review or refresh repository specs against implementation and tests.

gdsfactory/sax

Full checklist for adding a new transform to AlbumentationsX.

albumentations-team/AlbumentationsX

Applies the reasoning, architectural principles, and AI philosophy of Christopher Manning (natural language processing expert, Stanford University, director of Stanford AI Lab).

K-Dense-AI/mimeo

Review 3DGS implementation code for correctness, performance bugs, and best practices.

jaccen/Awesome-Gaussian-Skills

Load this FIRST whenever working with PyTorch CI data (any pytorch/ org repo), the torchci/HUD codebase, or the PyTorch HUD ClickHouse database.

pytorch/test-infra

Molecular machine learning toolkit. An agent skill from davila7/claude-code-templates.

davila7/claude-code-templates

Publish a Python package to PyPI using uv with credentials loaded from a local .secrets file.

ML4ITS/TimeVQVAE

Audits SKILL.md files in this repo's skills directory for references to functions, classes, or modules (mentioned by name in prose, e.g.

PINA-org/PINA

使用 PaddlePaddle 仓库规则评审 Pull Request 和全仓库代码变更，覆盖正确性、兼容性、算子、分布式、数值、性能、安全、测试、构建和 PR 信息。当需要审查 Paddle 的代码、测试、算子 YAML、C++/CUDA/XPU kernel、Python API、分布式逻辑或 CI 配置时使用。

PaddlePaddle/Paddle

A skill your agent uses when designing or reviewing self-distillation workflows for agentic models, including trace collection, teacher or judge feedback, rejection sampling, critique, conversion to…

burtenshaw/training-agents

Guide to using Mamba selective state-space models for linear-time sequence modeling, from the Mamba block and pretrained checkpoints to Mamba-2 and speed comparisons.

Orchestra-Research/AI-Research-SKILLs

Walks through nanoGPT, Karpathy's compact GPT implementation: training on Shakespeare, reproducing GPT-2, fine-tuning GPT-2 checkpoints and training on your own text.

Orchestra-Research/AI-Research-SKILLs

Explains RWKV, a hybrid that trains in parallel like a GPT and runs inference like an RNN with constant memory per token, plus usage, fine-tuning and troubleshooting.

Orchestra-Research/AI-Research-SKILLs

Rigor Train skill for deep learning research repositories. An agent skill from lllllllama/RigorPilot-Skills.

lllllllama/RigorPilot-Skills

Expert in PerforatedAI library for adding artificial dendrites to PyTorch neural networks.

PerforatedAI/PerforatedAI