AI & LLM Engineering · C++

A skill your agent uses when needing to compile, rebuild, or install Paddle from source after code changes.

PaddlePaddle/Paddle

Guide for adding Triton-backed CUDA operators to FastLLM. An agent skill from ztxz16/fastllm.

ztxz16/fastllm

A skill your agent uses when navigating Paddle eager-mode (dynamic graph) source code, tracing forward/backward execution, debugging autograd issues, understanding PyLayer, or investigating…

PaddlePaddle/Paddle

Read or write ONNX text format ("onnxtxt"). An agent skill from onnx/onnx.

onnx/onnx

Builds ONNX Runtime from source with its build scripts, explaining the update, build and test phases, key flags and where the build output lands.

microsoft/onnxruntime

Measures and shrinks the ExecuTorch runtime binary by building a size test, analyzing it with bloaty and landing each reduction as its own pull request.

pytorch/executorch

Builds ExecuTorch from source: the Python package, C++ runtime, model runners, Android and iOS cross-compilation and backend-specific builds, with environment checks.

pytorch/executorch

Drive an agentic loop that iteratively optimizes a GPU kernel for maximum speedup.

TongmingLAIC/AKO4ALL

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

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

Prepare a macOS or Ubuntu machine for edge-e3 development, diagnose missing Verilator/LLVM/Python dependencies, initialize the public repository, and answer or act on the example prompts in the root…

exeex/edge-cores

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

Write, debug, and optimize CUTLASS, CuTe, and CuTeDSL GPU kernels from local upstream source, examples, and headers.

slowlyC/agent-gpu-skills

GPU optimization workflow using uipc.profile, uipc.profile.nsight, and Nsight Compute CLI.

spiriMirror/libuipc

A skill your agent uses when writing, modifying, porting, or optimizing CuTe DSL GPU kernels in Python; reading CuTe DSL API reference material; integrating a CuTe DSL kernel into a project; or…

vipshop/cache-dit

Step-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang's jitkernel module

guqiong96/Lsglang

Scaffold new Celeritas source and test files with the required copyright header and register them in CMake.

celeritas-project/celeritas

Verify a CV-CUDA optimization campaign's deterministic definition-of-done and concise versioned MR summary per .agents/guidance/OPTIMIZATIONGUIDELINES.md.

CVCUDA/CV-CUDA

Runs the narrowest relevant tests to validate changes. An agent skill from noumena-labs/Sipp.

noumena-labs/Sipp

A skill your agent uses when writing, debugging, porting, reviewing, or optimizing CUTLASS or CuTe C++ kernels and templates; navigating CUTLASS examples, collectives, epilogues, pipelines, GEMM…

vipshop/cache-dit

Build vLLM (CPU) end-to-end with the oneDNN + ZenDNN (zen64) backend via direct integration (NO zentorch).

amd/ZenDNN

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

matlab/agent-skills-playground

Step-by-step tutorial for adding a heavyweight AOT CUDA/C++ kernel to sgl-kernel (including tests & benchmarks)

sgl-project/sglang

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

Explains where HOT-Step generation time goes (LM/DiT/VAE), how the TensorRT paths activate, how to benchmark from logs, and which knobs trade quality for speed.

scragnog/HOT-Step-CPP

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

intel/torch-xpu-ops

A checklist for upgrading the pinned ONNX version and opset in ONNX Runtime, covering the files to change, archive hashes, patch rebasing and release-candidate handling.

microsoft/onnxruntime

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

Review C++ changes for string parameter and call-site efficiency conventions (std::stringview, std::string&&, const std::string&, const char, and TransparentStringMap lookup).

tetherto/qvac

Verify a new CV-CUDA operator against the deterministic final regression checklist (the /make-op done-gate).

CVCUDA/CV-CUDA

Install or verify the AMD Quark package and its dependencies.

amd/Quark

Step-by-step tutorial for adding a new lightweight JIT CUDA kernel to sglang.kernels JIT infrastructure and public operator groups

sgl-project/sglang

Develop and profile the edge-e3 PyTorch-to-NNC flow, including nnc/compiler.py lowering and generated ABI, example/llama smoke models, cpp/libnn runtime operators, BF16 correctness checks, and…

exeex/edge-cores

Review a CV-CUDA operator's input-type, layout, dtype, and channel support matrix.

CVCUDA/CV-CUDA

Agent skill for sona-learning-optimizer - invoke with $agent-sona-learning-optimizer

ruvnet/ruflo

Run, extend, debug, or review the public edge-e3 bare-metal software harness, including encrypted Verilator builds, hello and tensor examples, all example/llama/model smoke cases, PyTorch BF16…

exeex/edge-cores

Build and run the public 64x64 x 128-token tiled circular tensor matmul example on the encrypted Edge Verilator simulator.

exeex/edge-cores

推論パスの canonical Python (exportonnx.py / vits/models.py:VitsModel.infer) を変更した PR で、6 ランタイム (Python runtime / Rust / Go / C / C++ / WASM) の inference path が追随しているかを git diff で確認。PR

ayutaz/piper-plus

Team-wide PR dashboard for the DevOps pod, scoped to PRs authored by pod-roster members.

tetherto/qvac

A skill your agent uses when compile time or startup time is the problem in code that uses Warp: a request to improve, optimize, or cut compile times; an app that is slow to start or stalls at the…

NVIDIA/skills

Understand and modify the pnpm+Nx consolidated CI — the generic -nx.yml leaves driven by each package's project.json options.ci.

tetherto/qvac

Explains how model files, checkpoints, GGUF quantization, and the Model Manager work in HOT-Step CPP.

scragnog/HOT-Step-CPP

GenieAPIService technical documentation retrieval. An agent skill from qualcomm/qai-appbuilder.

qualcomm/qai-appbuilder

A skill your agent uses for CUDA-Q setup, simulation targets, QPU access, and @cudaq.kernel authoring guidance.

NVIDIA/skills

Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI).

NVIDIA/skills

Maps every HOT-Step CPP feature to its route file, service, UI folder, and engine subsystem, including port topology and the browser-to-engine request path.

scragnog/HOT-Step-CPP

Generate C/C++ or CUDA code from an AI model (PyTorch, LiteRT) using MATLAB Coder or GPU Coder.

matlab/matlab-agentic-toolkit

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

matlab/matlab-agentic-toolkit