AI & ML
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
-
wenyi-li Bundle Rocm Crash DebugDebug ROCm/HIP kernel crashes in SGLang and vLLM on AMD GPUs (MI300X/MI325X/MI355X). Adapts SGLang's @debug_kernel_api kernel boundary logging to ROCm: captures input tensors before crash, tracks shapes/dtypes/values, dumps crash artifacts for offline analysis. Integrates with amdpilot executor failure_reason field and dashboard trajectory viewer. Triggered by: CUDA/HIP errors, illegal memory access, device-side assert, OOM kills, signal 137/139, NaN/Inf in outputs, "debug crash", "why did the trial fail".
- wenyi-li Skill Tilelang Cuda API
TileLang CUDA API 完整参考手册，适用于需要查阅具体 API 用法、了解函数参数含义的任意 TileLang CUDA 内核代码生成场景
- wenyi-li Skill Ncu Cuda Profiling
Automated NCU (Nsight Compute) profiling workflow with full metrics collection and persistent storage
- wenyi-li Bundle Perf Host Analysis
Analyze host/CPU overhead in TensorRT-LLM inference from nsys traces. Detect whether host overhead is the bottleneck using GPU idle ratio, host prep exposed ratio, and per-phase evidence. For regressions, isolate forward steps via allreduce/NVTX patterns, compare host operation breakdowns across versions, and identify scheduling or request-management overhead. Supports optional inter-kernel gap, eager-vs-graph, pattern mapping, and multi-rank straggler drill-down. Use standalone or within perf-analysis. Triggers: host overhead, inter-step gap, scheduling overhead, forward step isolation, nsys iteration analysis, NVTX breakdown, request management overhead, GPU idle, host bottleneck, host prep exposed, inter-kernel gap, bubble analysis, graph coverage, eager kernel, rank imbalance, straggler detection.
- wenyi-li Skill Sglang Diffusion Performance
Use when choosing the fastest SGLang Diffusion flags for a model, GPU, and VRAM budget.
- wenyi-li Bundle Debug Cuda Kernel Correctness
Skill: Debug CUDA Kernel Correctness
- wenyi-li Skill Gpu Architecture Fundamentals
This skill should be used when reasoning about GPU architecture fundamentals to guide kernel optimization choices such as memory hierarchy usage, execution model mapping, block sizing, and latency-aware tuning across HIP, Triton, and PyTorch.
- wenyi-li Skill Tilelang Cuda Synchronization
TileLang CUDA 同步规范，包括 T.sync_threads() 使用规则、线程安全最佳实践和死锁预防策略。适用于编写涉及共享内存访问、多线程协作、或需要避免同步死锁的 TileLang 内核代码生成场景
- wenyi-li Bundle Mi300 Hip Programming Insights
CDNA3/MI300 HIP programming insights—chiplet/cache model, Infinity Cache, memory coherency, matrix cores, sparsity, and best practices.
- wenyi-li Bundle Rocprofv3 Profiler
Profile AMD GPU kernels using rocprofv3 and analyze performance bottlenecks. Use when the user wants to profile HIP/ROCm kernels, identify GPU performance issues, analyze hardware counters, or understand why a kernel is slow on AMD GPUs (MI100, MI200, MI300 series). Provides wrapper scripts for rocprofv3 execution and automated parsing of profiler output into structured, agent-friendly JSON with bottleneck classification.
- wenyi-li Bundle Cuda Skill
Query NVIDIA PTX ISA 9.1, CUDA Runtime API 13.1, Driver API 13.1, Programming Guide v13.1, Best Practices Guide, Nsight Compute, Nsight Systems local documentation. Debug and optimize GPU kernels with nsys/ncu/compute-sanitizer workflows. Use when writing, debugging, or optimizing CUDA code, GPU kernels, PTX instructions, inline PTX, TensorCore operations (WMMA, WGMMA, TMA, tcgen05), or when the user mentions CUDA API functions, error codes, device properties, memory management, profiling, GPU performance, compute capabilities, CUDA Graphs, Cooperative Groups, Unified Memory, dynamic parallelism, CUDA programming model concepts, bank conflicts, shared memory optimization, warp divergence, memory coalescing, occupancy tuning, register pressure, L2 cache control, async copy, mbarrier, thread block clusters, or CUDA architecture questions (Ampere sm_80, Hopper sm_90, Blackwell sm_100).
- wenyi-li Skill Triton Cuda Basics
Triton CUDA 编程基础，包括核心概念（program_id、block、grid）、内核函数结构、装饰器用法和标准代码模式。适用于使用 Triton CUDA、需要了解基本语法结构的任意 CUDA 内核代码生成场景
- wenyi-li Skill Triton Cuda Matmul
矩阵乘法算子(matmul/bmm/linear)优化策略，包括分块 Tiling、共享内存缓存、Tensor Core 利用和大矩阵处理技巧。适用于实现 GEMM、批量矩阵乘、全连接层等矩阵运算的 CUDA 内核代码生成场景
- wenyi-li Skill Triton Cuda Memory
CUDA GPU 内存访问优化策略，包括共享内存利用、合并访存、Bank Conflict 避免和数据布局优化技巧。适用于内存带宽受限、需要优化全局内存访问效率、或处理大规模数据的 CUDA 内核性能优化场景
- wenyi-li Skill Cuda C Optimization
CUDA C 性能优化、数值稳定性和调试排查
- wenyi-li Bundle Cuda Code Generator
Generates optimized CUDA kernel code based on performance analysis reports or algorithm type. Reads NCU analysis reports (e.g. *_analysis.md) and optionally existing kernel code, then produces high-quality compilable .cu files with applied optimizations. Use when the user provides an NCU analysis report or requests CUDA kernel generation, optimization, or implementation of techniques like Shared Memory Tiling, vectorized loads, bank conflict elimination, or double buffering. Does not handle compilation, execution, or profiling.
- wenyi-li Bundle Kernel Cute Writing
Write and implement GPU kernels using NVIDIA CuTe DSL (CUTLASS 4.x Python API) — NOT for Triton, CUDA C++, or conceptual explanations. Trigger only when the user wants to write or implement a kernel, not when asking questions about CuTe DSL concepts or layouts. CuTe DSL uses cute.jit/cute.kernel decorators and cutlass.cute imports. Covers element-wise kernels, GEMM patterns, reductions, memory hierarchy (global/shared/register/TMA), MMA tensor core operations, software pipelining, and framework integration.
- wenyi-li Bundle Sglang Diffusion Benchmark Profile
Use when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.
- wenyi-li Bundle Perf Nsight Systems
Nsight Systems (nsys) CLI for system-level timeline profiling. Use when the user wants to run nsys profile, analyze .nsys-rep reports, use nsys stats/analyze/recipe commands, diagnose GPU idle time from timeline traces, or profile distributed training with NCCL overlap analysis. NOT for kernel-level metrics like SOL%, occupancy, or roofline (use perf-nsight-compute-analysis for ncu). NOT for writing or generating kernels. NOT for applying optimizations like CUDA Graphs.
- wenyi-li Skill Tilelang Cuda Basics
TileLang CUDA 核心概念、内核结构和标准编程模式
- wenyi-li Skill Tilelang Cuda Memory
TileLang CUDA 内存访问优化策略，包括 T.alloc_shared/fragment 使用、数据布局优化、合并访存和 Bank Conflict 避免技巧。适用于内存带宽受限、需要优化数据搬运效率的 TileLang 内核性能优化场景
- wenyi-li Skill Triton Cuda Patterns
Triton CUDA 三大核心编程模式（向量/逐元素、归约、矩阵乘法）的标准实现范式和代码模板。适用于需要快速确定算子属于哪种编程模式、或需要了解各模式基本代码结构的 CUDA 内核代码生成场景
- wenyi-li Bundle Kernel Triton Writing
ONLY for OpenAI Triton (@triton.jit) kernel development. NEVER use for CUDA C++ kernels, TileIR, or profiling tools (ncu, nsys). The user's request must involve Triton explicitly. Covers Triton-specific patterns: fused elementwise, reductions (softmax, LayerNorm, RMSNorm), tiled GEMM with triton.autotune, and flash attention. Workflow: design, write, verify (with fast-path for explicit requests).
- wenyi-li Skill Triton Cuda Attention
Attention 算子的 Triton-CUDA 实现指南。包含经过验证的 Flash Attention 完整示例、各变体（Causal/GQA/MQA/RoPE）的差异改法、在线 Softmax 算法和常见错误
- wenyi-li Skill Triton Cuda Debugging
Triton CUDA 调试排查清单和常见错误速查表，包括编译错误、运行时错误、精度问题和性能问题的诊断方法。适用于 CUDA 内核代码出现错误需要定位原因、或需要验证代码正确性的调试场景
- wenyi-li Bundle Perf Host Optimization
Profiles and optimizes TensorRT-LLM host/CPU overhead using line_profiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low or optimizing PyExecutor throughput.
- wenyi-li Bundle Perf Torch Cuda Graphs
Apply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch make_graphed_callables, TE make_graphed_callables, MCore CudaGraphManager, FullCudaGraphWrapper, manual torch.cuda.graph), code compatibility, capture workflows, dynamic pattern handling, and troubleshooting. Triggers: CUDA graph, torch.cuda.graph, make_graphed_callables, reduce-overhead, graph capture, graph replay, kernel launch overhead, CudaGraphManager, FullCudaGraphWrapper, full-iteration graph, stream capture.
- wenyi-li Skill Tilelang Cuda Patterns
TileLang CUDA 核心编程模式（逐元素、归约、矩阵乘法、GEMV）的标准实现范式和代码模板。适用于需要快速确定算子属于哪种编程模式、或需要了解 TileLang 各模式基本代码结构的内核代码生成场景
- wenyi-li Bundle Write Cuda Gemm Kernel
Skill: Write CUDA GEMM Kernel
- wenyi-li Bundle Amd Kernel Optimization
Optimize inference latency and throughput of PyTorch models on AMD GPUs (MI250/MI300/MI350) with ROCm. Use when profiling and optimizing GEMM, attention, elementwise ops, torch.compile, CUDAGraphs, or Triton kernels on AMD hardware. Covers the full optimize cycle: benchmark → profile → analyze → implement → verify. Also covers benchmarking methodology and common pitfalls that waste time.
- wenyi-li Bundle Perf Workload Profiling
Code instrumentation for timing workloads. Two scenarios: (1) Training loop — inject manual timing to report per-iteration latency, throughput (samples/sec), and data load time. (2) Standalone kernel/op — write CUDA event timing code with warmup, per-iteration statistics, and anti-pattern avoidance. Also covers NVTX annotation for labeling profiler timelines. NOT for: running or analyzing profiler tools (nsys, ncu, Nsight Systems, Nsight Compute), writing kernels (Triton, CuTe, CUDA), applying optimizations (CUDA Graphs, gradient checkpointing, fusion), or interpreting roofline/SOL% metrics. Triggers: "measure throughput", "benchmark this function", "time my training loop", "samples per second", "NVTX annotate", "instrument my dataloader", "data load time", "kernel timing", "how do I time".
- wenyi-li Skill Cuda C Examples Torch
PyTorch + CUDA C 完整集成示例代码
- wenyi-li Skill Triton Cuda Reduce
归约算子(reduce)优化策略，包含 sum/mean/max/min、softmax、layernorm、logsoftmax 等实现技巧。适用于需要在 CUDA GPU 上实现任意维度归约、规范化层或注意力分数计算的内核代码生成场景
- wenyi-li Skill Triton Cuda Error Fix
triton-cuda常见错误及修复方法，用于代码生成时避免同类问题
- wenyi-li Skill Triton Cuda Elementwise
逐元素算子(element-wise)优化策略，包括 add/mul/relu/sigmoid/tanh/gelu/exp/log 等操作的向量化实现和融合技巧。适用于实现激活函数、逐元素运算、广播操作等向量模式算子的 CUDA 内核代码生成场景
- wenyi-li Skill Triton Cuda Grid Config
Grid/Block 配置策略，包括线程块大小选择、SM 占用率优化和大 shape 算子处理方案。适用于需要确定 CUDA kernel 启动参数、优化 GPU 并行效率、或处理超大规模数据的内核代码生成场景
Frequently asked questions
What are AI & ML agent skills?
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
Which AI & ML skills are most installed?
Popular AI & ML skills on SkillMD right now include rocm-crash-debug, tilelang-cuda-api, ncu-cuda-profiling. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do AI & ML skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.